Speech-to-text system and speech-to-text program

Abstract

We provide a user-friendly speech-to-text conversion system. [Solution] The voice-to-text conversion system 1 comprises a first terminal that acquires the user's voice information and a second terminal that displays the character information obtained by converting the voice information in real time. By performing short-range communication between these terminals, the system provides a voice-to-text conversion system that is convenient and easy to operate for many users while ensuring the security of communication. Furthermore, the user can choose whether to acquire voice information acquired while the input operation unit is accepting user input (first voice information) or voice information acquired when the input operation unit accepts user input (second voice information).

Description

Technical Field

[0005] , , , , , , , , ,

[0006]

[0001] The present invention relates to a voice-to-text conversion system and a voice-to-text conversion program.

Background Art

[0002] In the daily operations of various industries, software for converting voice information into character information, so-called speech recognition, has been widely used. With the improvement of such technology, the convenience of using voice information, such as creating meeting minutes, has been significantly improved. In addition, since these information are stored as character data, it is also easy to search for and obtain necessary information later. Such technology helps improve the productivity of operations and is an essential technology especially in industries where operational efficiency is required.

[0003] For example, the promotion of digital transformation in medical sites such as hospitals is strongly demanded currently. This is because as the birthrate declines and the population ages, the increasing burden in medical institutions has become a problem. That is, while an increase in the number of people who need medical care such as the elderly is expected, the burden on doctors and the like increases, and there is a problem that appropriate medical services may not be provided.

[0004] Therefore, there is a demand for software that can reduce the workload of doctors and the like in medical sites and is easy to introduce.

[0005] Examples of such software that reduces the workload of doctors and the like include an electronic medical record that enables voice input. <000002[0]]

[0006] Patent Document 1 discloses an electronic medical record creation device including voice analysis means for analyzing voice and converting it into character information. In addition, Patent Document 2 discloses an invention related to character input of a mobile phone or the like.

Prior Art Documents

Patent Documents

[0007] [Patent Document 1] Japanese Patent Publication No. 2015-035099 [Patent Document 2] Japanese Patent Publication No. 2004-032275

[0008] However, when introducing such software and transcription devices, convenience and ease of use in the field become issues. For example, medical examinations don't always take place in an examination room; they may be conducted in a patient's room or other location for patients who have difficulty moving, or in special situations such as outdoors where it may be necessary to keep records.

[0009] On the other hand, typical transcription devices connect a microphone to a desktop or laptop computer and input audio through that microphone. However, there are cases where it is not possible to set up desktop computers at the site, and even laptop computers cannot be brought in. In particular, devices that store confidential information such as personal information should be isolated from areas accessible to patients, making them unsuitable for portability.

[0010] Thus, there is a need to separate the terminal used for inputting transcription data from the terminal used to store the information. Furthermore, it is preferable to be able to check the transcription results immediately. In particular, there is a need to use devices such as smartphones that users are familiar with as input devices.

[0011] On the other hand, using publicly accessible networks like the internet for communication can lead to problems such as eavesdropping. Special care is required, especially when transmitting personal information.

[0012] Patent document 1 does not describe the separation of terminals. Furthermore, Patent Document 2 does not describe the display of characters on the character information creation device 2, so its use and purpose are different. Also, it does not address security other than encryption in the communication network.

[0013] In addition to the above, those working busy jobs on-site are reluctant to adopt applications that are not user-friendly. However, whether an application's usability is perceived as good or bad is subjective and will inevitably vary from person to person. In other words, even if an application is easy to use for one user, if it's difficult to use for another, the application may ultimately be rejected, potentially delaying the implementation of digital transformation (DX) in the field. [Overview of the Initiative] [Problems that the invention aims to solve]

[0014] The problem we are trying to solve is the inability to provide a voice-to-text conversion system that is convenient and easy to use for many users while ensuring information security. [Means for solving the problem]

[0015] The present invention is most notably characterized by comprising a first terminal and a second terminal for short-range communication, wherein the first terminal is equipped with a voice information acquisition unit for acquiring user voice information, at least the first terminal or the second terminal is equipped with an information conversion unit for converting the voice information into text information, and the second terminal is equipped with a receiving-side text information display unit for displaying the text information on the display unit of the second terminal in real time.

[0016] This invention has been made in view of the above problems, and employs, for example, the following means. In other words, a speech-to-text conversion system comprising a first terminal for acquiring speech information and a second terminal for displaying text information obtained by converting the speech information in real time, The first terminal is, A voice standby display section that displays on the display section of the first terminal that voice acquisition is possible. A voice information acquisition section that acquires voice information of a user, and A short-distance communication transmission section that transmits the voice information and / or character information obtained by converting the voice information by short-distance communication, and is provided with The second terminal A short-distance communication reception section that receives the voice information and / or character information obtained by converting the voice information by short-distance communication, and A reception-side character information display section that displays the character information in real time on the display section of the second terminal, and is provided with Provided is a voice character conversion system, wherein at least one of the first terminal or the second terminal includes an information conversion section that converts the voice information into character information.

Effect of the Invention

[0017] The voice character conversion system of the present invention separates a first terminal that acquires voice information of a user from a second terminal that displays in real time character information obtained by converting the voice information, and further enables these to perform short-distance communication, thereby providing a voice character conversion system that is highly convenient and operable for many users while ensuring communication security.

Brief Description of the Drawings

[0018] [Figure 1] It is a diagram showing an outline of a voice character conversion system 1. [Figure 2] It is a diagram showing a connection destination selection screen. [Figure 3] It is a diagram showing a voice acquisition means selection screen (transceiver mode screen (before voice acquisition starts)). [Figure 4] It is a diagram showing a transceiver mode screen (during voice acquisition). [Figure 5] It is a diagram showing a recording mode screen (before voice acquisition starts). [Figure 6] It is a diagram showing a reception-side character display screen. [Figure 7]This diagram shows the receiving screen displaying multiple electronic medical records. [Figure 8] This is a flowchart showing the voice selection and acquisition process. [Figure 9] This is a flowchart showing the conversion and display process. [Figure 10] This is a hardware configuration diagram of the transmitting terminal 10. [Figure 11] This is a hardware configuration diagram of the receiving terminal 20. [Modes for carrying out the invention]

[0019] Embodiments of the present invention will be described with reference to the drawings. In the following embodiments, the same or corresponding parts may be denoted by the same reference numerals, and their descriptions may be omitted as appropriate. Furthermore, the drawings used below are for illustrative purposes only and may differ from the actual device configuration, user interface (UI), data structure, etc.

[0020] (Summary of the embodiment) The outline of this embodiment will be explained with reference to Figure 1. Figure 1 is a diagram showing an overview of the speech-to-text conversion system 1 according to this embodiment.

[0021] The voice-to-text conversion system 1 comprises a transmitting terminal 10 (10a to 10c in Figure 1) and a receiving terminal 20 (20a to 20c in Figure 1). The transmitting terminal 10 and the receiving terminal 20 communicate over short distances in accordance with standards such as Bluetooth®. The dotted line in Figure 1 indicates that the transmitting terminal 10 is receiving a signal emitted by the receiving terminal 20.

[0022] Here, the transmitting terminal 10 and the receiving terminal 20 are each equipped with a transmitting terminal-side application program P10 (hereinafter referred to as "App P10") and a receiving terminal-side application program P20 (hereinafter referred to as "App P20").

[0023] The program used by the speech-to-text conversion system 1 to achieve the objectives of this embodiment is referred to as "speech-to-text conversion program P1". The speech-to-text conversion program P1 includes programs (such as app P10 and app P20) used by the transmitting terminal 10 and the receiving terminal 20.

[0024] The following explanation will use an example of how the speech-to-text conversion system 1 is used in a medical institution. In this embodiment, the transmitting terminal 10 is a smartphone (hereinafter referred to as "smartphone"), and the receiving terminal 20 is a desktop or laptop personal computer (hereinafter referred to as "PC").

[0025] First, users such as doctors select their own PC (receiving terminal 20a), which is the destination for information transmission and is equipped with an electronic medical record system, from their smartphone (for example, sending terminal 10a). During the consultation, the doctor will input the information they want to enter into the electronic medical record into the voice input (microphone) of their smartphone. The voice can be, for example, the doctor's or the patient's voice.

[0026] At this time, the user can select the voice input method (transceiver mode, recording mode). For example, in the "transceiver mode" of this embodiment, audio input to the microphone is acquired while the input operation unit (button UI) is being operated by the user (first audio information acquisition). In other words, audio is acquired when the user is pressing (holding down) the button UI, and audio acquisition stops when the button UI is released. Furthermore, in the "recording mode" of this embodiment, the acquisition of audio input to the microphone begins when the input operation unit (button UI) is operated by the user (once) (second audio information acquisition). In recording mode, when the input operation unit (button UI) is operated by the user again, the acquisition of audio ends. In other words, when the user presses the button UI once, the acquisition of audio begins, and when the user presses the button UI again, the acquisition of audio ends.

[0027] The smartphone app P10 converts the audio information into text information and displays it on the smartphone's display, and also transmits the text information to the PC (receiving terminal 20) via short-range communication. The receiving terminal 20's PC displays the acquired text information on the electronic medical record on its monitor.

[0028] (Details of the embodiment) The following describes in detail the speech-to-text conversion system 1 according to this embodiment. The speech-to-text conversion system 1 includes a computer (transmitting terminal 10 and receiving terminal 20) equipped with a speech-to-text conversion program P1, and provides the user with a highly user-friendly speech-to-text conversion service (transcription service). In other words, the speech-to-text conversion system 1 is a system in which information processing by the speech-to-text conversion program P1 is concretely realized using hardware resources. The following describes, in order, the components that make up the speech-to-text conversion system 1: 1. User interface, 2. Program processing, 3. Data, and 4. Hardware configuration.

[0029] (Definition of terms) Here, I will define some terms. "Audio information" refers to information relating to sound. In principle, sound and voices acquired by microphones, etc., are considered audio, and audio information is the result of converting audio into electronic data. However, in the following, we will not strictly distinguish between the two. That is, sound and voices acquired by microphones, etc., may also be referred to as audio information. "Short-range communication" refers to direct communication between terminals that does not use communication networks such as intranets or the internet. It is a term used to distinguish it from communication that uses existing communication networks to which an unspecified number of terminals are connected. It can be wireless or wired. Examples of wireless communication include Bluetooth® and BLE (Bluetooth® Low Energy). The term "short-range" here is used to distinguish it from communication such as the internet, which can communicate over any distance as long as a communication network is laid out, and does not strictly limit the communication distance, but it is generally considered to be within 100m. "Real-time" means that processing occurs almost simultaneously. For example, it means displaying input voice information as text information almost simultaneously. The "almost simultaneous" here means that there is a time lag of a few seconds due to the processing involved from voice input to displaying text information, as well as communication processing, so it is not perfectly simultaneous but includes a time lag. The term "real-time" appears multiple times below, but since the processing time for each instance is different, the time represented by each instance of "real-time" is different. For example, in the embodiment described later, regarding the display of characters on the first terminal and the display of characters on the second terminal, there should be a time lag before the latter is displayed because communication is involved, but it is stated that both of these displays occur in real time. In addition to the above, terms are defined using quotation marks within the text.

[0030] In the following, when the term "○○ processing" is used, it means that the computer's processor executes processing based on the "○○" program stored in the program storage. The same word will be used in place of "○○" throughout this paragraph. In other words, the "○○" program is a program that makes the computer function as a "○○" means by executing the "○○" process. Furthermore, this means that the control unit equipped with the processor also functions as a "○○" unit (or "○○" device). In this case, the "○○" section means that it executes the "○○" process based on the "○○" program.

[0031] For example, the speech-to-text conversion program P1 is a program that causes a computer to function as a speech-to-text conversion means by executing speech-to-text conversion processing. In this case, the control unit of the computer equipped with a processor (transmitting terminal 10 and / or receiving terminal 20) functions as a speech-to-text conversion unit (or speech-to-text conversion device).

[0032] Similarly, each terminal that performs the selection screen display process, user selection acquisition process, voice standby display process, voice acquisition process, voice information acquisition process, volume-driven voice acquisition start process, volume-driven voice acquisition stop process, information conversion process, technical terminology conversion process, short-range communication process, short-range communication transmission process, short-range communication reception process, transmission log saving process, character information acquisition process, character information display process, transmitting side character information display process, receiving side character information display process, and character code conversion process functions as a selection screen display unit, user selection acquisition unit, voice standby display unit, voice acquisition unit, voice information acquisition unit, volume-driven voice acquisition start unit, volume-driven voice acquisition stop unit, information conversion unit, technical terminology conversion unit, short-range communication unit, short-range communication transmission unit, short-range communication reception unit, transmission log saving unit, character information acquisition unit, character information display unit, transmitting side character information display unit, receiving side character information display unit, and character code conversion unit, respectively.

[0033] In the speech-to-text conversion system 1, each terminal (computer), such as the transmitting terminal 10 and the receiving terminal 20, is equipped with a processor. Therefore, when simply referring to a processor, it means the processor that performs the processing related to the speech-to-text conversion program P1, i.e., the processor 111 of the transmitting terminal 10 and / or the processor 211 of the receiving terminal 20.

[0034] For simplicity, in the following, "the processor causes the memory unit (data storage unit) to save data" may be written as "the processor saves (data)." Similarly, the action of "the processor causing an input device such as an audio device to acquire sound" is sometimes described as "the processor acquires (causes) sound." Furthermore, the act of "the processor causing an output unit (browser, speaker, etc.) to output display, sound, etc." is sometimes described as "the processor displays (causes) the output." As described above, even if the actual functional unit being executed is different, the execution entity may still be described as the processor.

[0035] 1. User Interface (UI) First, the user interface that the speech-to-text conversion system 1 of this embodiment displays on the transmitting terminal 10, for example, a smartphone, will be explained with reference to a diagram. The interface described below is a simplified version of what app P10 displays in the browser of the sending terminal 10.

[0036] Furthermore, only icons related to functions necessary for explanation will be displayed, and other publicly known icons will be omitted. For example, the back button to return to the previously displayed page, the close button to close the screen, and the exit button to shut down the system are omitted.

[0037] Figure 2 shows the connection destination selection screen. The receiving terminal 20 enables the transmitting terminal 10 to find the connection destination through its communication function. In other words, the transmitting terminal 10 recognizes the presence of the receiving terminal 20 and displays the name of the receiving terminal 20 as a connection destination display icon UI-10a on the display unit 151.

[0038] The user operating the transmitting terminal 10 selects the appropriate destination (receiving terminal 20) from the destination display icon UI-10a. Once the user has made a selection and communication with the receiving terminal 20 is successfully established, the processor 111 of the transmitting terminal 10 displays the voice acquisition means selection screen described in the next section.

[0039] Figure 3 shows the screen for selecting the voice acquisition method. As shown in Figure 3, the processor 111 displays the voice acquisition means selection icon UI-10b, and the user selects the voice acquisition means (in this case, "transceiver mode" or "recording mode"). In other words, the smartphone's processor 111 obtains the user's choice of whether to acquire the first audio information via transceiver mode or the second audio information via recording mode. Figure 3 also shows the transceiver mode screen (before voice acquisition begins). While the user is pressing the voice acquisition button UI-111 (input operation unit 141) shown in Figure 3, the processor 111 acquires the voice. Next, I will explain the screen displayed during audio acquisition.

[0040] Figure 4 shows the transceiver mode screen (while voice acquisition is in progress). The processor 111 of the transmitting terminal 10 acquires the audio information input to the audio input unit 142.

[0041] As shown in Figure 4, the processor 111 of this embodiment converts the audio information input to the audio input unit 142 into text information in real time and displays it on the text information display unit UI-112.

[0042] In other words, in this embodiment, the conversion process from audio information to text information (hereinafter referred to as "information conversion process") is performed on the transmitting terminal 10. The method by which this information conversion process is performed on the receiving terminal 20 will be shown in the modified example described later.

[0043] Returning to Figure 4, here, the voice information of the doctor or patient, "I had abdominal pain from last night until this morning," is displayed on the screen as text. Note that the "|" after the phrase "~pain" in the diagram is the cursor (the same applies below). In this way, by displaying text information on the screen, doctors can verify whether the audio information has been correctly converted to text information.

[0044] In this embodiment, the display of the voice acquisition button UI-111 changes so that the user can visually understand that the button is pressed (voice acquisition button (operated) UI-111a in Figure 4). There are no particular restrictions on the display change as long as the content of the display changes, such as the color or shape of the button changing, or the button disappearing. Furthermore, the processor 111 displays the audio spectrum (UI-113) on the display unit 151 while acquiring audio.

[0045] Figure 5 shows the recording mode screen (before audio acquisition begins). This is the screen displayed by the processor 111 when the user selects "Recording Mode" on the audio acquisition method selection screen. When the user presses the voice acquisition start / stop button UI-121 (input operation unit 141) shown in Figure 5 once (by tapping it once or pressing and releasing it once), the processor 111 starts acquiring voice. When the user presses the voice acquisition start / stop button UI-121 (input operation unit 141) again, the processor 111 stops acquiring voice. Aside from the button UI, the screen UI during voice acquisition is the same as the UI in transceiver mode, so we will omit the explanation.

[0046] Figure 6 shows the receiving side's character display screen. The processor 211 of the receiving terminal 20 writes the character information obtained by converting the voice information into the electronic medical record that is open as an application. As shown in Figure 6, the cursor is in the symptoms field, and the processor 211 writes the text information converted from the speech (the same text information as shown in Figure 4) in real time.

[0047] As shown in Figure 6, the electronic medical record of this embodiment includes a patient section, a symptom section, and a findings section. The patient section contains the patient's personal information. This personal information may include, for example, name and age. It may also include other information such as medical history. Displaying patients' personal information helps prevent patient mix-ups and allows doctors to make more accurate diagnoses based on information such as age and medical history.

[0048] The symptoms section is for recording the patient's symptoms. Text information can be entered, regardless of whether it's a voice recording from the doctor or the patient.

[0049] The "Findings" section is where the physician's findings are recorded. This can be entered using the physician's voice recording. It may be possible to distinguish between the doctor's voice and the voices of third parties (nurses, patients, etc.) and allow only the doctor's voice to be entered.

[0050] In this embodiment, the cursor is generally placed in the symptoms field. However, it is not limited to this. The physician can select the input target by clicking on each field. For example, clicking on the findings field may activate the cursor in the findings field, causing voice input or other input to be output as text in the findings field.

[0051] Furthermore, the user, a doctor, can select input fields using voice commands. For example, if the voice input is "Patient Input," the patient field will be activated, and the cursor will automatically be placed at the end of the patient field. Similarly, if the voice input is "input symptoms," the symptoms field will be activated, and if it's "input findings," the findings field will be activated. In other words, the user can select the input destination for text information by inputting predetermined terms by voice (through the voice input unit 142).

[0052] Figure 7 shows a receiving screen displaying multiple electronic medical records. As shown in Figure 7, the display unit 251 of the receiving terminal 20 can display multiple electronic medical records. By selecting (activating) a window (input target), the user can input text information related to the speech-to-text conversion of this embodiment into the selected electronic medical record. In this embodiment, the user can activate any window by voice. For example, in Figure 7, when the voice input is "A Electronic Medical Record," the processor 211 activates the window for the A Electronic Medical Record system.

[0053] With the above configuration, users such as doctors can use their mobile devices as voice input devices (microphones) and utilize voice-to-text conversion functions while verifying that voice information is being correctly converted into text information in the field. In particular, users can choose between "transceiver mode" and "recording mode" according to their preference. They can choose based on ease of use, or, for example, in a noisy environment, they can choose transceiver mode to only capture audio when someone is speaking. In this case, there is the advantage of preventing background noise from being input as text information.

[0054] 2. Program Processing <Speech-to-text conversion processing> The program processing on the speech-to-text conversion system 1 in this embodiment will be described.

[0055] In this embodiment, the processor performs speech-to-text conversion processing based on the speech-to-text conversion program P1. The speech-to-text conversion program P1 includes at least a speech selection and acquisition program P11, a conversion and display program P12, a text conversion improvement program P13, and a speaker identification and display program P14. The following explains each of these points.

[0056] <2-1. Voice Selection Acquisition Process> The processor performs voice selection and acquisition processing based on the voice selection and acquisition program P11. In other words, the voice selection and acquisition program P11 causes the computer to function as a voice selection and acquisition means (voice selection and acquisition unit) by executing a voice selection and acquisition process by the processor.

[0057] In the voice selection and acquisition process of this embodiment, the processor 111 of the transmitting terminal 10 displays a screen for selecting the voice acquisition means (i.e., a screen for selecting whether to use transceiver mode or recording mode) and acquires the user's selection. In other words, the voice selection and acquisition process obtains the user's choice regarding whether to acquire the voice information as the primary voice information or the secondary voice information, and acquires the voice information according to that choice.

[0058] Here, the first audio information is audio information obtained by acquiring audio input to the audio input unit while the input operation unit is receiving user input. When the input operation unit is not receiving user input, it does not acquire audio input to the audio input unit. In other words, the first audio information in this embodiment is audio information acquired in transceiver mode. The second audio information is obtained when the input operation unit receives user input and begins acquiring the audio input to the audio input unit. The processor 111 terminates audio acquisition when the input operation unit receives user input again. In other words, the second audio information in this embodiment is audio information acquired in recording mode.

[0059] Here, the process by which the processor 111 displays a screen in which it selects either the first or second audio information (i.e., a screen in which it selects either transceiver mode or recording mode) is called the "selection screen display process," and the process by which the processor 111 acquires the user's selection at this time is called the "user selection acquisition process."

[0060] Furthermore, the voice selection and acquisition process of this embodiment includes the conversion and display process described later.

[0061] Figure 8 is a flowchart showing the voice selection and acquisition process. By launching application P10 on the receiving terminal 10, or by returning to the voice acquisition method selection screen, the processor 111 starts the voice selection and acquisition process. At this time, it is assumed that application P20 on the transmitting terminal 20 and the application program related to the electronic medical record are also running.

[0062] The processor 111 displays an audio acquisition means selection screen for the user to select either transceiver mode or recording mode (step 1).

[0063] At this time, the processor 111 displays the input operation unit 141 on the display unit 151 (see Figure 3). In this embodiment, the input operation unit 141 becomes the voice acquisition button UI-111 in transceiver mode, and the voice acquisition start / end button UI-121 in recording mode. However, the display timing of the input operation unit 141 is not limited to this. The processor 111 may also display the input operation unit 141 (the voice acquisition button UI-111 in transceiver mode, or the voice acquisition start / end button UI-121 in recording mode) after the branch in step 3 of the next section, that is, after selecting either transceiver mode or recording mode.

[0064] In summary, the processor 111 displays on the display unit (of the transmitting terminal 10) that voice acquisition is possible (referred to as "voice standby display processing"). In this embodiment, the indication that voice acquisition is possible is displayed on the button UI of the input operation unit 141 (voice acquisition button UI-111 or voice acquisition start / end button UI-121).

[0065] However, this is not the only option; a message indicating that voice input is being awaited may also be displayed. Furthermore, input operations are not limited to button UI; physical buttons (such as volume control buttons on a smartphone) may also be used.

[0066] Returning to Figure 8, we will first explain what happens when the user selects transceiver mode (Step 2: Yes).

[0067] While the user presses the voice acquisition button UI-111 and continues to hold it (Step 3: Yes), the processor performs the conversion and display process (Step 4). The conversion and display process will be described later.

[0068] On the other hand, if the user stops pressing the voice acquisition button UI-111 after pressing it (Step 3 No), and performs an exit operation (for example, pressing the close button or back button (not shown)) (Step 5 Yes), various data, including temporarily stored voice information, text information, and information including transmission date and time information for short-range communication, are saved to (for example, auxiliary memory) (Step 6), and the voice selection and acquisition process is terminated. Information including transmission date and time information for short-distance communications will be referred to as the "transmission log." Examples of the data stored here will be provided in the Data section.

[0069] Although not shown in Figure 8, if the user performs a termination operation, the processor 111 saves the information (step 6) and terminates the voice selection acquisition process, regardless of which step it is currently in.

[0070] If the user stops pressing the voice acquisition button UI-111 (step 3 No) and does not perform a termination operation (step 5 No), the processor 111 waits for the button to be pressed again.

[0071] In this embodiment, the data saved in step 6 includes voice information, text information obtained by converting the voice, patient information (such as name), and processing date and time information (e.g., transmission log). The processor also stores the voice information and text information in association. Further details will be explained in the data section.

[0072] The process of saving transmission logs, which include transmission date and time information for short-distance communications, is referred to as the "transmission log saving process."

[0073] Next, we will explain what happens when the user selects recording mode (Step 2 No.).

[0074] In recording mode, once the user presses the audio acquisition start / end button UI-121 (Step 7 Yes), the processor performs the conversion and display process (Step 8). In this embodiment, although there is no difference in the processing content between the conversion and display processing in step 4 and step 8, the processor 111 distinguishes and records which mode the data is from.

[0075] Next, even if the voice acquisition start / end button UI-121 is not pressed (Step 7 No), if the voice input unit 142 of the transmitting terminal 10 detects a volume level above a certain level (Step 9 Yes), and this continues for a certain period of time (x seconds) or longer (Step 10 Yes), the processor also performs the conversion and display process (Step 8).

[0076] This allows the processor to automatically acquire speech and convert it into text, even if the user forgets to initiate the speech acquisition process. The above-mentioned volume level, i.e., the volume level at which voice acquisition begins (hereinafter referred to as the "first volume"), can be set by the user. Similarly, the above-mentioned time required to begin voice acquisition (hereinafter referred to as the "first time," corresponding to x seconds in Figure 8) can also be set by the user.

[0077] If the audio input unit 142 of the transmitting terminal 10 does not detect a volume level above a certain level (Step 9 No), or if the audio input unit 142 detects a volume level above a certain level but this does not continue for a certain period of time or longer (Step 10 No), the processor 111 returns to determining whether the audio acquisition start / end button UI-121 has been pressed (Step 7).

[0078] In summary, the processor 111 starts voice acquisition if the voice input unit detects a sound at or above a predetermined first volume level for a predetermined first time, even if there is no user operation of the input unit (in this case, the voice acquisition start / end button UI-121). This process is called the "volume-driven audio acquisition start process".

[0079] Returning to Figure 8, if the voice acquisition start / end button UI-121 is pressed again after it has been pressed (voice acquisition stop operation - step 11 Yes), the processor 111 stops acquiring voice (step 12), saves various data such as the acquired data (step 6), and terminates the voice selection and acquisition process.

[0080] Here, even if the voice acquisition start / end button UI-121 is not pressed (step 11 No), if the volume of the voice detected by the voice input unit 142 of the transmitting terminal 10 falls below a certain level (step 13 Yes), and this continues for a certain period of time (y seconds) or longer (step 14 Yes), the processor 111 also stops acquiring the voice (step 12).

[0081] This allows the processor to automatically stop voice acquisition and store voice information, even if the user forgets to stop voice acquisition. Furthermore, the volume level below which audio acquisition is terminated (hereinafter referred to as the "second volume level") can be set by the user. Similarly, the time period for stopping audio acquisition (hereinafter referred to as the "second time period," corresponding to y seconds in Figure 8) can also be set by the user.

[0082] If the volume detected by the audio input unit 142 of the transmitting terminal 10 is above a certain level (step 13No), or if the volume detected by the audio input unit 142 is below a certain level but does not remain below that level for a certain period of time (step 14No), the processor 111 continues the conversion and display process (step 8).

[0083] In summary, after starting voice acquisition, the processor 111 stops voice acquisition if the voice input unit does not detect a sound at a predetermined second volume level or higher for a predetermined second period of time or longer. This process is called the "volume-driven audio acquisition stop process".

[0084] In this embodiment, the user can disable the functions related to the volume-driven audio acquisition start process and / or volume-driven audio acquisition stop process. This is to prevent audio acquisition from starting or stopping automatically. If the volume-driven audio acquisition start process is disabled, and no button is pressed in step 7, (Step 7 No) wait for the button to be pressed (return to step 7). If the volume-driven audio acquisition stop process is disabled, and no stop operation is performed, (Step 11 No) continue the conversion display process (return to step 8).

[0085] With this configuration, users can switch between transceiver mode and recording mode depending on the situation. Furthermore, the volume-driven audio acquisition start process prevents forgetting to record, and the volume-driven audio acquisition stop process prevents forgetting to stop recording while audio acquisition is in recording mode.

[0086] A previous challenge was that when using speech-to-text conversion software or transcription devices, necessary information could not be obtained due to forgetting to start the devices, etc. For example, if you start recording by operating the control panel (buttons, switches, etc.) on the recording device, you won't be able to record audio if you forget to do so. On the other hand, another option is to start recording when a certain volume level is detected. However, in this case, the recording may start unnoticed, continue for an extended period, and strain the storage capacity of the device.

[0087] In particular, in the case of the latter type of device, if it is the type that deletes old data and records new data when the storage capacity runs out (i.e., overwrites data), even past data may be erased.

[0088] Furthermore, if the device does not delete old data or record new data when its storage capacity is full (i.e., it simply stops recording), then recording will not be possible. In particular, in situations such as medical examinations, the failure to record information can lead to situations where appropriate medical care cannot be provided, so a comprehensive system is required to prevent such occurrences.

[0089] In other words, software that has the function of converting audio information into text information had the problem of not being able to prevent the loss of audio information.

[0090] The speech-to-text conversion system 1 according to this embodiment has the advantage of preventing the forgetting of speech, as it combines the function of acquiring speech input into the speech input unit by operating the input operation unit and the function of detecting speech input from the speech input unit and automatically starting speech acquisition.

[0091] <2-2. Conversion and Display Processing> The processor performs conversion and display processing based on the conversion and display program P12. In other words, the conversion and display program P12 enables the computer to function as a conversion and display means (conversion and display unit) by executing the conversion and display process by the processor.

[0092] In the conversion and display processing of this embodiment, the processor 111 of the transmitting terminal 10, (1) Voice information acquisition process that acquires voice information as primary or secondary voice information based on the user's voice information, in particular, based on the user's selection. (2) Information conversion process that converts the audio information into text information, (3) A transmitting character information display process that displays the character information in real time on the display unit of the transmitting terminal 10, and (4) A short-range communication transmission process is performed to transmit the character information via short-range communication.

[0093] Furthermore, in the voice selection and acquisition process, the processor 211 of the receiving terminal 20, (5) Short-range communication receiving process that receives text information (obtained by converting the above audio information) via short-range communication. (6) A character information acquisition process that acquires character information by converting the audio information to be acquired as the first or second audio information based on the user's selection. (7) The receiving terminal 20 performs a character information display process, which displays the character information in real time on the display unit of the receiving terminal 20.

[0094] Figure 9 is a flowchart showing the conversion and display process. The conversion and display process is a subroutine of the voice selection and acquisition process described above. The processor starts the conversion and display process upon receiving an operation from the user to initiate voice acquisition.

[0095] For simplicity, Figure 9 shows the processing of processor 111 and processor 211 in this embodiment together. In other words, steps 21 to 24 are processed by processor 111, and steps 25 and 26 are processed by processor 211. In other words, for a smartphone, one processing step is completed from voice acquisition (step 21) to sending text information (step 24), while for a PC, one processing step is completed from receiving text information in step 24 to displaying the text information on the display unit 251 (step 28). The following explains each step.

[0096] The processor 111 acquires sound through the audio input unit 142 (microphone) (step 21).

[0097] The processor 111 converts the acquired audio information into text information (information conversion process, step 22).

[0098] The processor 111 displays the character information obtained by converting the voice information on the display unit 151 (smartphone screen) in real time (referred to as "transmitter-side character information display processing," step 23), and also transmits at least the above-mentioned character information to the receiving terminal 20 via short-range communication (step 24).

[0099] The processor 211, which acquires character information via short-range communication, obtains the position on the display unit 251 where the acquired character information is displayed (character display position acquisition process, step 25). Here, the position on the display unit 251 refers to the position where the cursor is activated in an input field within the electronic medical record (such as the symptom field mentioned above).

[0100] Next, the processor 211 displays the acquired character information in real time on the display unit 251 (electronic medical record) of the receiving terminal 20 (PC) (referred to as "receiving character information display processing" - step 26).

[0101] After displaying the text information on the display unit 151 (smartphone screen) of the transmitting terminal 10 and the display unit 251 (electronic medical record) of the receiving terminal 20, the processor returns a response.

[0102] As mentioned above, Figure 9 uses a single flowchart for convenience, but since the terminals for steps 23-24 and steps 25-26 are different, each process is executed separately. Furthermore, because communication processing is involved, the term "real-time" in step 23 and the term "real-time" in step 26 differ in processing time (there is a time lag). However, as defined above, the term "real-time" in this specification is a concept that includes cases where the processing times differ.

[0103] In step 21, the process of acquiring audio information through an input unit such as the audio input unit 142 (microphone), whether as first audio information or second audio information, is referred to as the "audio acquisition process".

[0104] In other words, the "audio information acquisition process" (as described in (1) above), which acquires audio information as either the first or second audio information based on the user's selection, refers to the audio acquisition process performed according to the user's selection. The user selection referred to here means the user's choice of whether to acquire the audio as primary audio information (audio information in transceiver mode) or as secondary audio information (audio information in recording mode) (see "User Selection Acquisition Process" above).

[0105] In step 22, a known method is used as the technique for converting audio information into text information. For example, technologies that use large-scale language models (LLMs), such as generative AI, can be cited.

[0106] Furthermore, when converting this audio information into text information, the processor 111 performs the conversion while referring to the specialized terminology dictionary database D30 provided in the memory unit 12. This prevents mistranslations of less common technical terms.

[0107] In other words, the storage unit 12 of the transmitting terminal 10 is equipped with a specialized terminology dictionary database, and the processor 111 performs a specialized terminology conversion process that converts specialized terms contained in the voice information into text information based on the specialized terminology dictionary database.

[0108] In step 24, the processor 211 of the receiving terminal 20 receives the character information via short-range communication. The processing performed by the transmitting terminal 10 (processor 111) at this time is referred to as "short-range communication transmission processing," and the processing performed by the receiving terminal 20 (processor 211) is referred to as "short-range communication reception processing."

[0109] Furthermore, the process of performing short-range communication will be referred to as "short-range communication processing." In other words, short-range communication processing includes short-range communication transmission processing and / or short-range communication reception processing.

[0110] Furthermore, in this embodiment, the processor 211 acquires character information through short-range communication reception processing. In other words, the processor 211 obtains character information by converting the audio information to be acquired as either first or second audio information based on the user's selection. This process on the processor 211 side is called "character information acquisition process".

[0111] Here, the processing performed by processor 211, "(6) above, character information acquisition processing to acquire character information obtained by converting the voice information acquired as first voice information or second voice information based on the user's selection," means acquiring character information obtained by the processing performed by processor 111, "(1) above, voice information acquisition processing to acquire voice information as first voice information or second voice information based on the user's selection, and (2) above, information conversion processing to convert the voice information into character information." In this embodiment, processor 211 does not convert voice information into character information.

[0112] In this embodiment, the processor 111 transmits not only text information but also audio information. The data will be explained in the data section.

[0113] In step 25, the initial cursor position in this embodiment is predetermined and is, in principle, at the end of the symptom field. Since the most frequently used mode is filling in the symptom field, this has the advantage of speeding up input.

[0114] In step 26, the process of displaying the text information obtained by converting the audio information is referred to as the "text information display process." The text information conversion process includes the sender's text information display process and / or the receiver's text information display process.

[0115] Here, the speech-to-text conversion system 1 performs character code conversion on the text information according to the application program of the electronic medical record. For example, in this embodiment, the processor 211 converts the acquired character information to "Unicode (UTF-8)" and pastes it into the electronic medical record. More precisely, it uses the character information for pasting that is encoded in UTF-8 format using code points assigned in Unicode according to the character.

[0116] For example, by converting audio information into text information, pasting it to the clipboard, and then using that text information, it becomes possible to handle many electronic medical record systems.

[0117] Because electronic medical record applications (hereinafter referred to as "electronic medical record applications") use different character encodings depending on the manufacturer, pasting the text information generated on the sending terminal 10 directly will result in garbled characters. Therefore, by performing the above processing, the processor 211 can display the text correctly without garbling, regardless of which electronic medical record application the text output destination is.

[0118] The processor 211 performs these operations automatically, but the user may choose whether to do so. For example, the P20 app could allow users to select the character encoding. The selectable character encodings could include, for instance, ASCII, JIS, Shift-JIS, and EUC. Please note that the examples listed here are just a few examples, and you can use any known encoding such as EUC-JP, UTF-8, UTF-16, UTF-16LE, or UTF-16BE.

[0119] In summary, the processor 211 performs a character code conversion process to convert the character code to match the display format of the target application program.

[0120] <2-3. Character Conversion Improvement Process> The processor performs character conversion improvement processing based on the character conversion improvement program P13. In other words, the character conversion improvement program P13 enables the computer to function as a character conversion improvement means (character conversion improvement unit) by executing character conversion improvement processing by the processor (not shown).

[0121] In the character conversion improvement process of this embodiment, the processor 111 of the transmitting terminal 10, (1) Using the audio information and corresponding text information from the audio-text information database (described below), as well as information regarding the accuracy of the audio information, as training data, a machine learning model that has learned about the correspondence between the audio information and the text information, (2) Takes audio information as input and obtains corresponding text information as output.

[0122] Furthermore, the processor 111 displays the character information acquired as output of the machine learning model on the display unit 151 and also transmits it to the receiving terminal 20.

[0123] The information related to correctness here includes, for example, training data where incorrect parts are left as they are and marked as incorrect, and training data where incorrect parts are corrected and marked as correct.

[0124] These processes relate to machine learning training and inference. In this embodiment, the machine learning itself is performed on a terminal other than the transmitting terminal 10 or the receiving terminal 20 (for example, a machine learning server), and the machine learning model for character conversion improvement processing obtained through learning is stored in the transmitting terminal 10 and used.

[0125] <2-4. Speaker Identification Display Processing> The processor performs speaker identification and display processing based on the speaker identification and display program P14. In other words, the speaker identification display program P14 causes the computer to function as a speaker identification display means (speaker identification display unit) by executing speaker identification display processing by the processor (not shown).

[0126] The speaker identification and display processing is a process that identifies the speaker and changes the display mode on the display unit for each identified speaker. In this embodiment, the speaker is identified during the information conversion processing stage (such processing is referred to as "speaker identification processing"), and the display mode is changed for each identified speaker on the display unit 251 of the receiving terminal 20, for example. This makes it easier to identify who said what, even after the audio information has been converted into text.

[0127] Furthermore, in this embodiment, in order to achieve this identifiable display, a machine learning model is used that uses at least the speaker's voice as training data for speaker identification. For example, a machine learning model that uses a vector of cepstrum coefficients as features can be used for this purpose.

[0128] In the speaker identification display process of this embodiment, the processor 111 of the transmitting terminal 10, (1) For a machine learning model that learns the relationship between speakers and speech information using speech information labeled for each speaker as training data, (2) The system takes the speaker's voice as input and obtains the speaker's name as output.

[0129] Furthermore, the processor 111 displays the speaker's name, which was obtained as the output of the machine learning model, on the display unit 151 and also transmits it to the receiving terminal 20.

[0130] In this context, the label is, for example, the speaker's name. In other words, the voice information of a certain person and that person's name become the training data.

[0131] These processes relate to machine learning training and inference. In this embodiment, the machine learning itself is performed on a terminal other than the transmitting terminal 10 or the receiving terminal 20 (for example, a machine learning server), and the machine learning model for speaker identification processing obtained through learning is stored in the transmitting terminal 10 and used.

[0132] The speaker identification display process enables the identification of the doctor's voice and the patient's voice in the input field (symptom field) of the electronic medical record on the receiving terminal 20, and makes them distinguishable (for example, by using different colors). For this purpose, a machine learning model for speaker identification processing could, for example, use at least the voices of doctors and third parties as training data. For example, by inputting a patient's voice, the system infers which patient the voice belongs to and displays it clearly on the display unit 251.

[0133] 3. Data The data handled by the speech-to-text conversion system 1 of this embodiment will be explained below with reference to the figures. The speech-to-text conversion system 1 includes a speech-to-text conversion database D1. The data is stored in the storage unit (data storage unit 12b or data storage unit 22b) of the transmitting terminal 10 or the receiving terminal 20. The speech-to-text conversion database D1 of this embodiment includes a character information database D10, a patient database D20, and a specialized terminology dictionary database D30.

[0134] In this embodiment, the transmitting terminal 10 is equipped with a character information database D10 and a specialized terminology dictionary database D30 in its storage unit 12. The receiving terminal 20's storage unit 22 is equipped with a patient database D20. Both the transmitting terminal 10 and the receiving terminal 20 may be equipped with these databases.

[0135] The character information database D10 is a database that contains data related to character information (character data).

[0136] [Table 1]

[0137] Table 1 shows an example of the data contained in the character information database D10. As shown in Table 1, the character information database D10 of this embodiment includes the following items: voice character ID, transmission date and time, voice information file name, character information file name, and type.

[0138] A speech-to-text ID is a unique string of characters assigned to each piece of text information. The transmission date and time is the date and time when the audio and / or text information was transmitted. This data is related to the transmission log mentioned above. The audio information file indicates the file name of the audio information file that stores the audio information. In other words, the data storage unit 12b contains the audio information file indicated by the audio information file name. Any known file format can be used for the audio information file as appropriate. For example, AIFF, MP3, FLAC, WAVE, AAC (registered trademark), etc. The character information file indicates the name of the character information file that stores the character information. In other words, the data storage unit 12b contains the character information file indicated by the character information file name. Any known file format can be used for the character information file as appropriate, such as a .txt file.

[0139] In this embodiment, since date and text information are stored in association with each other, users can search for document information (medical records) by date or text (words, etc.).

[0140] In summary, in this embodiment, the transmitting terminal 10 converts voice information into text information, and the storage unit 12 of the transmitting terminal 10 includes a database (referred to as the "voice-to-text information database") that stores voice information and the text information corresponding to each voice piece in association.

[0141] Patient database D20 is a database that contains data about patients (patient data). In this embodiment, for security reasons, the patient database D20 is stored only in the storage unit 22 (data storage unit 22b) of the receiving terminal 20.

[0142] [Table 2]

[0143] Table 2 shows an example of the data contained in patient database D20. As shown in Table 2, the patient database D20 of this embodiment includes the following items: patient ID, patient personal information (name, contact information, etc.), information about the illness such as the date of hospitalization and the name of the illness, and voice-character ID. A patient ID is a unique string assigned to each patient. The voice-to-text ID is data used to link a patient with the above-mentioned text data. For example, patient ID 000001, Mr. Suzuki ○ro, has two voice-to-text IDs associated with him, indicating that there are two pieces of text information from this system.

[0144] Because patient information is stored in the patient database D20, for example, when a doctor speaks "Suzuki ○ro" or "Mr. ○ro" into the voice input unit 142 of the transmitting terminal 10, the receiving terminal 20 retrieves the medical record of that person and enters an input waiting state. In other words, voice commands can be used to call up (activate) the input destination for text information (electronic medical record application) on the receiving terminal 20.

[0145] Furthermore, the speech-to-text conversion system 1 includes the aforementioned specialized terminology dictionary database D30 in the storage unit 12 (data storage unit 12b) of the transmitting terminal 10. The technical terminology dictionary database D30 of this embodiment is a database in which audio information and text information related to medical technical terms are stored in a linked manner (not shown). The D30 specialized terminology dictionary database has the advantage of accurately converting spoken language input by users such as doctors into text.

[0146] If there are errors in the text information obtained through the conversion of voice information, the user can correct them on the receiving terminal 20. If a correction is made, the processor 211 stores the voice information linked to the corrected text information. The specialized terminology dictionary database D30 accumulates more information the more the speech-to-text conversion system 1 is used, making it possible to provide a speech-to-text conversion system 1 with fewer errors.

[0147] For example, the processor 111 receives voice input related to a word, refers to the string in the specialized terminology dictionary database D30, and selects the appropriate term.

[0148] In addition to the above, the data may also include voice data of doctors and data related to machine learning models that use doctors' voice data as training data.

[0149] With the configuration described above, the database of this embodiment not only stores text information but also stores corresponding audio information, so that incorrectly converted text information can be corrected later. This allows for the creation of a machine learning model using the parts of the audio and text information that match and those that do not, and by using this machine learning model, highly accurate speech-to-text conversion can be achieved. Medical terminology is highly unique, and training data for everyday conversation, for example, is insufficient. Therefore, this type of data structure has the advantage of being particularly useful for improving machine learning models.

[0150] 4. Hardware Configuration As shown in Figure 1, the speech-to-text conversion system 1 in this embodiment includes a transmitting terminal 10 and a receiving terminal 20. The transmitting terminal 10 and the receiving terminal 20 each have software (app P10 and app P20) installed for operating the speech-to-text conversion system 1 according to this embodiment, and various processes are executed according to the functions of this software. Apps P10 and P20 function as part of the speech-to-text conversion program P1. The following describes each piece of hardware.

[0151] <Sending terminal 10> The transmitting terminal 10 is an information processing device for the user to use the speech-to-text conversion system 1, and includes an application P10. In particular, the transmitting terminal 10 is equipped with a function to acquire voice information through the voice input unit 142 as an essential feature.

[0152] In this embodiment, the transmitting terminal 10 is a smartphone. However, the transmitting terminal 10 is not limited to a smartphone; it may be a portable terminal other than a smartphone, such as a tablet, or it may not be a portable terminal as long as it is equipped with the necessary devices such as the voice input unit 142 (for example, a desktop computer). However, from the standpoint of convenience, it is preferable that the transmitting terminal 10 is a portable terminal.

[0153] In Figure 1, one transmitting terminal 10 is shown per user, but the number is not limited to this.

[0154] Figure 10 is a hardware configuration diagram of the transmitting terminal 10. As shown in Figure 10, the transmitting terminal 10 comprises a control unit 11, a storage unit 12, and a communication control unit 13. The control unit 11 also comprises a processor 111, a ROM 112, a RAM 113, and a timing unit 114. In this embodiment, the processor 111 is a CPU (Central Processing Unit). I will explain the basic functions of each of them in detail later.

[0155] A control unit 11 equipped with a processor 111 and a control unit 22 equipped with a processor 211 (described later) constitute and function as a speech-to-text conversion unit (not shown). The speech-to-text conversion unit executes a speech-to-text conversion program P1 to perform speech-to-text conversion processing.

[0156] Furthermore, one program may include other programs. For example, in this embodiment, the speech-to-text conversion program P1 includes a speech selection and acquisition program P11 and a conversion and display program P12, etc.

[0157] As shown in Figure 10, the storage unit 12 includes a program storage unit 12a and a data storage unit 12b, and stores programs and data necessary for various processes. For example, the program storage unit 12a stores not only the application P10 according to this embodiment, but also control programs for controlling devices connected to the transmitting terminal 10, such as a communication control program for controlling the communication control unit 13. For example, when a user launches app P10, it executes various processes, such as allowing the user to select a communication destination.

[0158] In this embodiment, application P10 is installed on the receiving terminal 20 via internet communication or a storage medium.

[0159] As shown in Figure 10, the communication control unit 13 is a device that communicates with an external terminal.

[0160] In particular, in this embodiment, the communication control unit 13 includes a transmitting short-range communication unit 131 and performs short-range communication with the receiving terminal 20. Furthermore, there is a one-to-one correspondence between the transmitting terminal 10, which acquires audio, and the receiving terminal 20, which displays text information.

[0161] The transmitting short-range communication unit 131 is a device that utilizes a communication method defined by IEEE 802.15 (e.g., Bluetooth®, BLE). In other words, the transmitting short-range communication unit 131 is a device for performing peer-to-peer communication or broadcast communication with the receiving terminal 20. Generally, in this embodiment, the receiving terminal 20 is referred to as the parent, and the transmitting terminal 10 as the child.

[0162] This is distinct from communication that takes place over a network, such as the internet. Network-based communication includes, for example, wired communication methods defined by IEEE 802.3 and IEEE 802.5, and wireless communication methods defined by IEEE 802.11 (so-called Wi-Fi).

[0163] In other words, the short-range communication unit 131 allows the transmitting terminal 10 to communicate with the receiving terminal 20, which is not connected to a network. This means that terminals located in physically distant locations cannot connect, and because it does not connect to a communication network where unspecified terminals are connected, such as the internet, a high level of security can be maintained. Furthermore, since communication using the short-range communication unit 131 is possible without physical cables, it has the advantage of being easy to carry the terminal (transmitting terminal 10).

[0164] The input unit 14 is a device that receives input from the user. The input unit 14 of this embodiment includes an input operation unit 141 and an audio input unit 142.

[0165] The input operation unit 141 is a functional unit that receives user input. In particular, in this embodiment, the processor 111 displays at least the input operation unit 141, which accepts user input and initiates voice input, on the display unit 151.

[0166] In the above-described embodiment, the input operation unit 141 becomes the voice acquisition button UI-111 in transceiver mode, and the voice acquisition start / end button UI-121 in recording mode.

[0167] In this embodiment, the transmitting terminal 10 is a smartphone and is equipped with a touch panel as the input unit 14. The input operation section 141 consists of UI elements such as icons and buttons (UI-10a, UI-10b, UI-111, or UI-121, etc.) that are placed on the surface of the display section 151 (smartphone screen).

[0168] In this embodiment, the audio input unit 142 is a microphone built into the smartphone. The audio input unit 142 converts audio into electrical signals (audio signals, audio data, audio information). The processor 111 acquires audio information, which is converted from sound into electrical signals, through the audio input unit 142. For simplicity, the process of converting sound into electrical signals may be omitted in some descriptions.

[0169] In addition to the above, the transmitting terminal 10 may be equipped with additional devices necessary for the use of this embodiment, or devices to improve convenience for the use of this embodiment.

[0170] In summary, the transmitting terminal 10 is: • A voice information acquisition unit that acquires voice information as either first or second voice information based on the user's selection. • Information conversion unit that converts the aforementioned audio information into text information. • A transmitting character information display unit that displays the aforementioned character information in real time on the display unit (of the transmitting terminal 10), and, The system includes a short-range communication transmission unit that transmits the acquired character information via short-range communication to a terminal (receiving terminal 20) that displays the character information in real time.

[0171] <Receiving terminal 20> The receiving terminal 20 is an information processing device for the user to use the speech-to-text conversion system 1, and is equipped with an application P20. Furthermore, in this embodiment, the receiving terminal 20 is equipped with a commercially available application program related to electronic medical records (electronic medical record application) in addition to the application P20. In particular, the receiving terminal 20 is equipped with an essential function: the ability to display text information obtained by converting audio information in real time.

[0172] In this embodiment, the receiving terminal 20 is a desktop or laptop personal computer (PC). However, the receiving terminal 20 is not limited to these and may be a portable terminal such as a tablet. However, for security reasons, the receiving terminal 20 should preferably be a desktop PC that is difficult to take off the premises.

[0173] In Figure 1, only one receiving terminal 20 is shown per user, but the number is not limited to one and may be implemented using multiple computers.

[0174] Figure 11 is a hardware configuration diagram of the receiving terminal 20. As shown in Figure 11, the receiving terminal 20 comprises a control unit 21, a storage unit 22, a communication control unit 23, an input unit 24, and an output unit 25. The control unit 21 also comprises a processor 211, ROM, RAM, and a timing unit. In this embodiment, the processor 211 is a CPU (Central Processing Unit). Explanations that overlap with previously explained content or relate to basic functions described later will be omitted.

[0175] The application P20 according to this embodiment is stored (installed) in the program storage unit 22a of the receiving terminal 20, and the processor 211 executes various processes according to the functions of the software.

[0176] Various processes include output (e.g., screen display) based on information obtained from the transmitting terminal 10, receiving user input, and various communications. For example, when a user launches the P20 app, it will reside in the taskbar and begin accepting text messages.

[0177] In this embodiment, application P20 is installed on the receiving terminal 20 via internet communication or a storage medium.

[0178] As shown in Figure 11, the communication control unit 23 is a device that communicates with an external terminal.

[0179] In particular, in this embodiment, the communication control unit 23 includes a transmitting-side short-range communication unit 231 and performs short-range communication with the transmitting-side terminal 10. The specifications for the transmitting short-range communication unit 231 are as described above and will be omitted here.

[0180] In this embodiment, the display unit 251 is a display attached to a PC. In particular, the acquired text information is displayed on the electronic medical record displayed on the display unit 251.

[0181] In summary, the receiving terminal 20 is a short-range communication receiving unit that performs short-range communication with the terminal that acquires voice information (transmitting terminal 10). A character information acquisition unit that acquires character information by converting the audio information to be acquired as either first or second audio information based on the user's selection. A receiving character information display unit that displays the aforementioned character information on the display unit of the receiving terminal 20 in real time. It is equipped with.

[0182] The speech-to-text conversion system 1 may also include devices other than those described above. For example, separate terminals for machine learning (such as machine learning servers and data storage) may be provided.

[0183] (Explanation of the basic functions of a computer) The following describes the control unit (processor, ROM, RAM, timing unit), storage unit, communication control unit, input unit, and output unit. Except for the short-range communication described above, the connection configuration (network topology) between functional units is not particularly limited in any of the terminals of this embodiment. For example, it may be a bus type, a star type, a mesh type, or the like.

[0184] The processor performs information processing and controls various devices according to programs stored in ROM or other memory units. In this embodiment, the processor is a CPU (Central Processing Unit).

[0185] However, the processor is not limited to a CPU. Various processors such as CPUs, DSPs (Digital Signal Units), GPUs (Graphics Processing Units), GPGPUs (General Purpose computing on GPUs), ASICs (Application Specific Integrated Circuits), or FPGAs (Field Programmable Gate Arrays) may be used individually or in combination. For example, a processor that integrates a CPU and a GPU is called an APU (Accelerated Processing Unit), and such a processor can also be used.

[0186] ROM is read-only memory that contains various programs and data pre-stored for the processor to perform various control and calculations.

[0187] RAM is random-access memory used by the processor as working memory. Various areas can be reserved within this RAM for performing the various processes described in this embodiment.

[0188] The timing unit performs timing processing, including the acquisition of time information. If the computer is equipped with a communication control unit, it may acquire time information from an external source using NTP (Network Time Protocol).

[0189] A memory unit is a device for storing information such as programs and data. It is also called a storage unit. The memory unit can be either internal or external.

[0190] The storage unit includes a storage medium capable of reading and writing data, and a drive for reading and writing to the storage medium. Storage media include internal and external types, such as HD (hard disk), CD-ROM, and flash memory. Examples of drives include HDDs (hard disk drives) and SSDs (solid state drives).

[0191] The memory unit comprises a program storage unit and a data storage unit as functional units. The program storage unit stores control programs for controlling various devices, such as communication control programs for controlling communications.

[0192] The communication control unit is a device for facilitating communication between terminals and other devices. The communication control unit connects the terminal equipped with the communication control unit to an internet communication network.

[0193] The communication method of the communication control unit is a known method, and either a wired or wireless method is applied depending on the equipment. For example, if the device is a desktop PC, both wired and wireless connections are possible, while if the device is a smartphone, a wireless communication method is possible.

[0194] For wired connections, communication methods defined in standards such as IEEE 802.3 (e.g., bus-type or star-type wired LANs) can be suitably used, but other communication methods such as those defined in IEEE 802.5 (e.g., ring-type wired LANs) may also be used.

[0195] For wireless communication, a communication method defined by, for example, IEEE 802.11 (e.g., Wi-Fi) can be suitably used. However, other methods such as IEEE 802.15 (e.g., Bluetooth®, BLE (Bluetooth® Low Energy)), IEEE 802.16 (e.g., WiMAX), ZigBee®, 920MHz band wireless (e.g., Wi-SUN), or optical communication methods such as infrared communication may also be used.

[0196] The input and output sections are devices responsible for input and output to and from the terminal, respectively. The input and output sections are sometimes collectively referred to as the input / output section. The input unit is a device that receives input from the user. Examples of such input units include keyboards, pointing devices such as mice, trackpads, tablets, or touch panels.

[0197] If the device is a tablet or smartphone and the input unit is a touch panel, the input unit is located on the surface of the display unit that displays images, such as a touchscreen. In this case, the input unit identifies the user's touch position corresponding to the various operation icons displayed on the display unit and accepts input from the user.

[0198] The output unit is a device for outputting, for example, images, audio, or documents. Output devices include, for example, display devices such as touchscreens and displays (liquid crystal displays and organic EL displays), audio output devices such as speakers, and document output devices such as printers.

[0199] With the above configuration, the transmitting terminal 10 and the receiving terminal 20 are separate, allowing users such as doctors to bring the transmitting terminal 10 into the medical field. For example, when a doctor makes rounds to a patient's room, they can carry the transmitting terminal 10 and input voice information while listening to the patient's condition. After the rounds, when the doctor returns to the examination room or room where the receiving terminal 20 is located and opens the screen, the input voice information has been converted into text and entered into each patient's medical record, thus reducing the doctor's input burden. Since the transmitting terminal 10 and the receiving terminal 20 communicate via short-range communication and do not use the internet, there is an advantage in that highly sensitive personal information such as the patient's medical condition can be prevented from being leaked through eavesdropping or other means.

[0200] (Other embodiments) Up to this point, we have explained the use of speech-to-text conversion system 1 using examples from medical institutions, but we will now explain other use cases.

[0201] The speech-to-text conversion system 1 may be used, for example, in educational settings. In this case, the output destination for the text information will be a teacher's logbook or similar document, rather than an electronic medical record. Since audio information in schools and other similar settings may contain personal information of students, the speech-to-text conversion system 1 is preferably used.

[0202] Furthermore, the speech-to-text conversion system 1 may also be used at construction sites. For example, it may be used to transmit information such as structural evaluations of buildings at the construction site from a transmitting terminal 10, such as a smartphone, to a receiving terminal 20 located in an office. The speech-to-text conversion system 1 is particularly suitable for use when on-site evaluations or other processes involve technical secrets.

[0203] (modified version) The present invention is not limited to the embodiments described above, but includes various modifications to the embodiments described above, without departing from the spirit of the invention.

[0204] In the embodiment described above, it is assumed that both the application P10 on the transmitting terminal 10 and the application P20 on the receiving terminal 20 are running, but this is not limited to this. In other words, if the application P20 (or the application program related to the electronic medical record) on the receiving terminal 20 is not running, the application P10 on the transmitting terminal 10 may store the acquired information in its storage unit and perform the necessary processing when the application P20 on the receiving terminal 20 is started. The memory unit referred to here may be the memory unit of an external device, not just the control unit 12. For example, if a communication connection is established, it may be the memory unit of a server.

[0205] In the embodiment described above, the transmitting terminal 10 transmitted both voice information and text information to the receiving terminal 20 simultaneously, but the transmitting terminal 10 may transmit only text information. In this case, the audio information may not be sent at all, or it may be sent at a different time. In this case, the data saved during the voice selection and acquisition process will also be a transmission log of text information, rather than voice information. In this case, there is the advantage that the amount of data transmitted in real time is reduced.

[0206] In the embodiment described above, the conversion process from voice information to text information was performed on the transmitting terminal 10, but it is not limited to this, and the conversion process from voice information to text information may also be performed on the receiving terminal 20. In this case, the conversion and display processing flow described above changes. Specifically, the display of character information on the transmitting terminal 10 (step 23) is eliminated, and the order of processing from voice acquisition onward also changes. For example, after acquiring the audio, the processor 111 of the transmitting terminal 10 transmits the audio information to the receiving terminal 20 (via short-range communication). The processor 211 that acquires the information (via short-range communication) converts the audio information into text information, obtains the display position of the text information, and then displays it. In this case, the transmission log is a transmission log of voice information, and speaker identification processing is also performed on the receiving terminal 20. However, if the conversion process from voice information to text information is performed on the transmitting terminal 10, the text information can be displayed on the display unit 151 (smartphone screen), which has the advantage of allowing the user who is inputting the voice information to check the text information more quickly. It is also possible to convert the voice information into text information on the receiving terminal 20 before sending it to the transmitting terminal 10, but in this case, the number of communications between terminals would increase. Therefore, it is considered faster to perform the voice-to-text conversion on the transmitting terminal 10 and display the text information on the transmitting terminal 10.

[0207] In addition to the embodiments described above, the speech-to-text conversion system 1 may also include a relay device that relays communication between the transmitting terminal 10 and the receiving terminal 20. In this case, in order to maintain the security of communications, it is preferable that the relay device is independent of everything except the speech-to-text conversion system 1 (i.e., it does not communicate with anything other than terminals within the speech-to-text conversion system 1). In this case, there is the advantage of extending the communication range.

[0208] Aspects of the present invention including this embodiment, in other words, have the following features. The following corresponds to the scope of the claims at the time of filing of the present application. However, it may differ from the description of the scope of the claims after the amendment of the scope of the claims after filing. (1) In a first aspect, there is provided a voice-character conversion system including a first terminal that acquires voice information and a second terminal that displays in real time character information obtained by converting the voice information. The first terminal includes a voice standby display unit that displays on a display unit of the first terminal that voice acquisition is possible, a voice information acquisition unit that acquires voice information of a user, and a short-distance communication transmission unit that transmits the voice information and / or character information obtained by converting the voice information by short-distance communication. The second terminal includes a short-distance communication reception unit that receives the voice information and / or character information obtained by converting the voice information by short-distance communication, and a reception-side character information display unit that displays the character information on a display unit of the second terminal in real time. At least one of the first terminal or the second terminal includes an information conversion unit that converts the voice information into character information. (2) In a second aspect, there is provided a voice-character conversion system including a first terminal that acquires voice information and a second terminal that displays in real time character information obtained by converting the voice information. The first terminal includes a voice standby display unit that displays on a display unit of the first terminal that voice acquisition is possible, a voice information acquisition unit that acquires voice information of a user, an information conversion unit that converts the voice information into character information, and a short-distance communication transmission unit that transmits the character information by short-distance communication. The second terminal includes a short-distance communication reception unit that receives the character information by short-distance communication, and a reception-side character information display unit that displays the character information on a display unit of the second terminal in real time. In this case, since the voice information is converted into character information on the first terminal on the transmission side, the character information can be displayed on the first terminal side. (3) In the third aspect, the voice information acquisition unit that acquires the voice information of the user is a voice information acquisition unit that acquires voice information as first voice information or second voice information based on the user's selection. The first voice information is voice information obtained by acquiring the voice input to the voice input unit while the input operation unit is receiving the user's operation. The second voice information is voice information obtained by starting to acquire the voice input to the voice input unit while the input operation unit is receiving the user's operation. A voice character conversion system according to the first or second aspect is provided, characterized in that. In this case, since the recording method can be changed arbitrarily by the user, the convenience of the user is significantly improved. In the above-described embodiment, since each person has a preference for either the transceiver mode or the recording mode, the introduction hurdle can be lowered by covering such individual preferences. (4) In the fourth aspect, the first terminal further includes a volume-driven voice acquisition start unit that starts voice acquisition when a state in which the voice input unit detects a voice at or above a predetermined first volume continues for a predetermined first time or longer even when there is no operation of the input operation unit by the user. A voice character conversion system according to the first or second aspect is provided, characterized in that. In this case, there is an advantage of preventing forgetting to record. In particular, since examinations and the like cannot be repeated, preventing forgetting to record improves the convenience of the user. (5) In the fifth aspect, the first terminal further includes a volume-driven voice acquisition stop unit that stops voice acquisition when a state in which the voice input unit does not detect a voice at or above a predetermined second volume continues for a predetermined second time or longer after voice acquisition starts. A voice character conversion system according to the first or second aspect is provided, characterized in that. In this case, there is an advantage of preventing forgetting to stop recording. Preventing forgetting to stop recording reduces wasteful use of files. (6) In a sixth embodiment, the audio-to-text conversion system according to the first or second embodiment is provided, further characterized in that the storage unit of the first terminal or the second terminal comprises a specialized terminology dictionary database, and a specialized terminology conversion unit converts the specialized terminology contained in the audio information into text information based on the specialized terminology dictionary database. In this case, even when highly specialized conversations take place, such as in the medical industry, the system can correctly display text information from audio data, improving user convenience. (7) The seventh embodiment provides a speech-to-text system according to the first or second embodiment, characterized in that the second terminal further comprises a character code conversion unit that converts character codes to conform to the display format of the application program to be output. In this case, there is an advantage in that character corruption is less likely to occur, even when outputting to different electronic medical record systems from different manufacturers, or when the destination application program is different. (8) In an eighth aspect, the first terminal further comprises a transmission log storage unit that stores a transmission log including transmission date and time information of the short-range communication, thereby providing the speech-to-text conversion system according to the first or second aspect. In this case, the date and time of the audio can be accurately saved, which has the advantage of allowing users to check the audio and text information later. Furthermore, information retrieval can be performed using date and time searches. (9) In the ninth aspect, the system further comprises a voice-to-text database in which at least one of the first terminal or the second terminal stores voice information and corresponding character information, and (1) a character conversion improvement unit that takes voice information as input and outputs character information corresponding to the voice information, to a machine learning model that learns about the correspondence between voice information and character information using the voice information and character information corresponding to the voice information in the voice-to-text database as learning data, and (2) a character conversion improvement unit that takes voice information as input and outputs character information corresponding to the voice information. In this case, there is the advantage that the accuracy of speech recognition will be higher even if the input speech contains technical terms. Furthermore, recognition accuracy will improve even if the speech is difficult to understand due to, for example, the speaker's articulation. (10) In a tenth embodiment, at least one of the first terminal or the second terminal is further provided with a speaker identification display unit that identifies a speaker and changes the display mode on the display unit for each identified speaker, and the speaker identification display unit is characterized by (1) providing a machine learning model that learns the relationship between speakers and speech information using speech information labeled for each speaker as training data, and (2) taking the speaker's speech as input and obtaining the speaker's name of the speech as output. In this case, the speaker is clearly displayed, which has the advantage of improving usability. (11) In the eleventh embodiment, a voice-to-text conversion system is provided, comprising: a voice standby display unit that displays on a display unit that voice acquisition is possible; a voice information acquisition unit that acquires voice information as first voice information or second voice information based on the user's selection; an information conversion unit that converts the voice information into text information; a transmitting-side text information display unit that displays the text information on a display unit in real time; and a short-range communication transmission unit that transmits the text information to a terminal that displays the acquired text information in real time via short-range communication, wherein the first voice information is voice information obtained by acquiring voice input into the voice input unit while the input operation unit is accepting user operations, and the second voice information is voice information obtained when the input operation unit accepts user operations and starts acquiring voice input into the voice input unit. This concerns the first device (for example, a smartphone). (12) In the twelfth aspect, a speech-to-text conversion system is provided, comprising: a short-range communication receiving unit that communicates with a terminal for acquiring voice information and receives the information; a character information acquisition unit that acquires character information obtained by converting the voice information to be acquired as first voice information or second voice information based on the user's selection; and a receiving-side character information display unit that displays the character information on a display unit in real time, wherein the first voice information is voice information obtained by acquiring voice input into the voice input unit while the input operation unit is accepting user operations, and the second voice information is voice information obtained when the input operation unit accepts user operations and starts acquiring voice input into the voice input unit. This concerns a second device (for example, a PC). (13) In a thirteenth aspect, a voice-to-text conversion program is provided, characterized in that a first terminal for acquiring voice information functions as a voice standby display means for displaying on the display unit of the first terminal that voice acquisition is possible, a voice information acquisition means for acquiring user voice information, and a short-range communication transmission means for transmitting the voice information and / or character information obtained by converting the voice information via short-range communication; a second terminal for displaying the character information obtained by converting the voice information in real time functions as a short-range communication receiving means for receiving the voice information and / or character information obtained by converting the voice information via short-range communication, and a receiving-side character information display means for displaying the character information on the display unit of the second terminal in real time; and at least one of the first terminal or the second terminal is equipped with an information conversion means for converting the voice information into character information. [Industrial applicability]

[0209] Since the transmitting terminal 10 is portable, it is particularly effective when you want to easily perform transcription by carrying the transmitting terminal 10 around within the same building or similar location. In particular, because it does not use the internet, it can be applied to applications where you want to prevent the leakage of confidential information such as personal information due to eavesdropping or man-in-the-middle attacks. [Explanation of symbols]

[0210] 1 Voice-to-Text Conversion System 10 Transmitting Terminal (Smartphone (Smartphone)) 11 Control Unit 111 Processor 112 ROM 113 RAM 114 Timing Unit 12 Storage Unit 12a Program Storage Section 12b Data Storage Section 13 Communication Control Unit 131 Transmitting Side Short-Range Communication Unit 14 Input Unit 141 Input Operation Unit (Button) 142 Voice Input Unit (Microphone) 15 Output Unit 151 Display Unit (Smartphone Screen) 20 Receiving Terminal 21 Control Unit 211 Processor 22 Storage Unit 22a Program Storage Section 22b Data Storage Section 23 Communication Control Unit 231 Receiving Side Short-Range Communication Unit 24 Input Unit 25 Output Unit 251 Display Unit (Display, Electronic Medical Record Display Unit) UI-10 Transmitting Terminal Screen UI-10a Connection Destination Display Icon UI-10b Voice Acquisition Method Selection Icon UI-110 Transceiver Mode Screen UI-111 Voice Acquisition Button<T UI-111a Voice Acquisition Button (During Operation) UI-112 Character Information Display Section UI-113 Audio Spectrum UI-120 Recording Mode Screen UI-121 Voice Acquisition Start / End Button UI-20 Receiving Terminal Screen P1 Speech-to-Text Program P10 Sending terminal application program (App P10) P11 Voice Selection Acquisition Program P12 Conversion and Display Program P13 Text Conversion Improvement Program P14 Speaker Identification Program P20 Receiving terminal application program (App P20) D1 Speech-to-Text Database D10 Character Information Database D20 Patient Database D30 Specialized Terminology Dictionary Database

Claims

1. A speech-to-text conversion system comprising a first terminal for acquiring voice information and a second terminal for displaying text information obtained by converting the voice information in real time, The first terminal is, A voice standby display unit that indicates on the display unit of the first terminal that voice acquisition is possible. A voice information acquisition unit that acquires user voice information, and A short-range communication transmission unit that transmits the aforementioned voice information and / or character information obtained by converting the aforementioned voice information via short-range communication. Equipped with, The second terminal is, A short-range communication receiving unit that receives the aforementioned voice information and / or character information obtained by converting the aforementioned voice information via short-range communication, A receiving character information display unit that displays the aforementioned character information on the display unit of a second terminal in real time. Equipped with, A speech-to-text conversion system characterized in that at least one of the first terminal or the second terminal is equipped with an information conversion unit that converts the speech information into text information.

2. A speech-to-text conversion system comprising a first terminal for acquiring voice information and a second terminal for displaying text information obtained by converting the voice information in real time, The first terminal is, A voice standby display unit that indicates on the display unit of the first terminal that voice acquisition is possible. Voice information acquisition unit that acquires user voice information, An information conversion unit that converts the aforementioned audio information into text information, and A short-range communication transmission unit that transmits the aforementioned character information via short-range communication. Equipped with, The second terminal is, A short-range communication receiving unit that receives the aforementioned character information via short-range communication, and A receiving character information display unit that displays the aforementioned character information on the display unit of a second terminal in real time. A speech-to-text conversion system characterized by comprising the following features.

3. The voice information acquisition unit that acquires the voice information of the user said, This is a voice information acquisition unit that acquires voice information as either first voice information or second voice information based on the user's selection. The first audio information is audio information obtained by acquiring audio input to the audio input unit while the input operation unit is accepting user operations. The speech-to-text conversion system according to claim 1 or 2, characterized in that the second voice information is voice information obtained when the input operation unit receives a user operation and starts acquiring the voice input to the voice input unit.

4. The speech-to-text conversion system according to claim 1 or 2, further comprising a volume-driven speech acquisition start unit that starts speech acquisition when the speech input unit has detected a sound at or above a predetermined first volume for a predetermined first time, even when there is no operation of the input unit by the user.

5. The speech-to-text conversion system according to claim 1 or 2, further comprising a volume-driven speech acquisition stop unit that stops speech acquisition if, after the start of speech acquisition, the speech input unit does not detect speech at a predetermined second volume level or higher for a predetermined second period of time or longer.

6. Furthermore, the storage unit of the first terminal or the second terminal is equipped with a specialized terminology dictionary database. The speech-to-text conversion system according to claim 1 or 2, further comprising a specialized term conversion unit that converts specialized terms contained in the speech information into text information based on the specialized term dictionary database.

7. The speech-to-text conversion system according to claim 1 or 2, further characterized in that the second terminal comprises a character code conversion unit that converts character codes to conform to the display format of the output application program.

8. The speech-to-text conversion system according to claim 1 or 2, characterized in that the first terminal further comprises a transmission log storage unit that stores a transmission log including transmission date and time information of the short-range communication.

9. Furthermore, at least one of the first or second terminals has a storage unit that includes a voice-to-text information database that stores the voice information and the corresponding text information in association with each voice information, (1) Using the audio information and corresponding text information from the aforementioned audio-text information database, as well as information regarding its accuracy, as training data, a machine learning model that has learned about the correspondence between the audio information and the text information, (2) The speech-to-text conversion system according to claim 1 or 2, characterized in that it includes a character conversion improvement unit that takes speech information as input and obtains character information corresponding to the speech information as output.

10. Furthermore, at least one of the first terminal or the second terminal is equipped with a speaker identification display unit that identifies the speaker and changes the display mode on the display unit for each identified speaker. The speaker identification display unit is, (1) For a machine learning model that learns the relationship between speakers and speech information using speech information labeled for each speaker as training data, (2) The speech-to-text conversion system according to claim 1 or 2, characterized in that it takes the speaker's voice as input and obtains the speaker's name as output.

11. A voice standby display unit that indicates on the display unit that voice acquisition is possible. A voice information acquisition unit that acquires voice information as either first voice information or second voice information based on the user's selection. Information conversion unit that converts the aforementioned audio information into text information, A transmitting character information display unit that displays the aforementioned character information on the display unit in real time, and A short-range communication transmission unit transmits the acquired character information via short-range communication to a terminal that displays the character information in real time. Equipped with, The first audio information is audio information obtained by acquiring audio input to the audio input unit while the input operation unit is accepting user operations. The second audio information is characterized by being audio information obtained when the input operation unit receives a user operation and starts acquiring the audio input to the audio input unit. Speech-to-text conversion system.

12. A terminal that acquires voice information and a short-range communication receiver unit that receives the information, A character information acquisition unit that acquires character information by converting the audio information to be acquired as either first or second audio information based on the user's selection, and A receiving character information display unit that displays the aforementioned character information on the display unit in real time. Equipped with, The first audio information is audio information obtained by acquiring audio input to the audio input unit while the input operation unit is accepting user operations. The second audio information is characterized by being audio information obtained when the input operation unit receives a user operation and starts acquiring the audio input to the audio input unit. Speech-to-text conversion system.

13. The first terminal that acquires voice information is A voice standby display means that displays on the display unit of the first terminal that voice acquisition is possible. A means for acquiring voice information of a user, and Short-range communication transmission means for transmitting the aforementioned voice information and / or character information obtained by converting the aforementioned voice information via short-range communication. To make it function as, A second terminal that displays the text information obtained by converting the aforementioned audio information in real time, A short-range communication receiving means for receiving the aforementioned voice information and / or character information obtained by converting the aforementioned voice information via short-range communication, Receiving character information display means that displays the aforementioned character information in real time on the display unit of the second terminal. To make it function as, A speech-to-text conversion program characterized in that at least one of the first terminal or the second terminal is equipped with information conversion means for converting the speech information into text information.

Images