Information processing apparatus, information processing method, and information processing program

Abstract

To provide an information processor capable of evaluating whether or not a collected voice is accurately heard.SOLUTION: A generation unit that generates first text data from first voice data and generates second text data from second voice data obtained by collecting a sound derived from the first voice data, and an evaluation unit that evaluates voice clarity of an environment in which the second voice data is collected using the first text data and the second text data.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Patent Document 1 discloses a technology relating to a speaking style evaluation device, a speaking style evaluation method, and a program for evaluating the intelligibility of speech based on an input speech signal. Patent Document 1 discloses a speaking style evaluation device including a speech evaluation value calculation unit that calculates, based on the input speech signal, one or more of a speech rate evaluation value that evaluates the speed of speech, an intonation evaluation value that evaluates the intonation of speech, and an intelligibility evaluation value that evaluates the intelligibility of speech, and outputs the calculated value as a speech evaluation value; and a score calculation unit that calculates a total score for the input speech signal based on the speech evaluation value when two or more of the speech rate evaluation value, the intonation evaluation value, and the intelligibility evaluation value are calculated. Patent Document 2 also discloses a technology relating to a vocabulary evaluation device, a vocabulary evaluation method, and a vocabulary evaluation program for accurately evaluating a subject's vocabulary ability. Patent Document 2 discloses a system including: a word collection means for collecting words included in a target person's utterance via a terminal connected to the system so as to be able to communicate; an environment acquisition means for acquiring the environment in which the utterance was made based on information from the terminal; and an analysis means for analyzing the target person's acquisition status of the words for each of the environments. The present invention discloses a vocabulary assessment device comprising: [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-197621 [Patent Document 2] Japanese Patent Application Publication No. 2024-60181 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, online conference systems using the Internet have become widespread. When an online conference is held by connecting a conference room and another room via the Internet, it is important for the smooth running of the conference that the voices picked up in the conference room can be accurately heard in the other room.

[0005] The present disclosure has been made in consideration of the above points, and aims to provide an information processing device, an information processing method, and an information processing program that are capable of evaluating whether a picked-up voice can be heard accurately. [Means for solving the problem]

[0006] According to one aspect of the present disclosure, an information processing device is provided, comprising: a generation unit that generates first text data from first audio data and generates second text data from second audio data obtained by collecting sound derived from the first audio data; and an evaluation unit that uses the first text data and the second text data to evaluate the audio clarity of the environment in which the second audio data was collected.

[0007] The evaluation unit may evaluate the speech clarity using a matching rate between the first text data and the second text data.

[0008] The evaluation unit may evaluate the speech clarity using a matching rate for each phrase between the first text data and the second text data.

[0009] The first audio data may be audio data that is not affected by the environment.

[0010] The first audio data may be audio data acquired through a network.

[0011] According to another aspect of the present disclosure, there is provided an information processing method in which a processor generates first text data from first audio data, generates second text data from second audio data obtained by collecting sound derived from the first audio data, and performs a process of evaluating the speech clarity of the environment in which the second audio data was collected using the first text data and the second text data.

[0012] According to another aspect of the present disclosure, an information processing program is provided that causes a computer to generate first text data from first audio data, generate second text data from second audio data obtained by collecting sound derived from the first audio data, and use the first text data and the second text data to perform a process of evaluating the audio clarity of the environment in which the second audio data was collected. [Effects of the Invention]

[0013] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and an information processing program that are capable of evaluating whether a picked-up voice can be heard accurately. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram illustrating an overview of an embodiment of the disclosed technology. [Figure 2] FIG. 2 is a block diagram showing a hardware configuration of the information processing device. [Figure 3] 1 is a block diagram illustrating an example of a functional configuration of an information processing device; [Figure 4] 10 is a flowchart showing a flow of information processing by an information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of the present disclosure will be described below with reference to the drawings. The same reference numerals are used throughout the drawings to designate identical or equivalent components and parts. The dimensional proportions of the drawings are exaggerated for illustrative purposes and may differ from the actual proportions.

[0016] FIG. 1 is a diagram illustrating an overview of this embodiment. The information processing device 10 illustrated in FIG. 1 is a device for evaluating the voice clarity of a conference room 1. Specifically, the information processing device 10 uses first voice data transmitted from a personal computer 2 installed in the conference room 1 via a network 3 and second voice data obtained by collecting sound derived from the first voice data emitted from a speaker 4 with a microphone 5 installed in the conference room 1 and transmitted from the personal computer 2 via the network 3 to evaluate the voice clarity of the conference room 1, which is the environment in which the second voice data is collected. By using the first voice data and the second voice data, the information processing device 10 can evaluate whether the voice collected in the conference room 1 can be accurately heard. The first voice data is pre-recorded, for example, on a smartphone 6, and is output from the speaker 4 by connecting the smartphone 6 to the speaker 4. The first voice data transmitted from the personal computer 2 via the network 3 is data that is not affected by the environment (conference room 1 in the example of FIG. 1).

[0017] In this embodiment, the area of ​​the conference room 1 is 75 m 3 The equivalent noise level of the sound emitted from the speaker 4 is 65 dBA, and the distance between the speaker 4 and the microphone 5 is 6 meters.

[0018] When evaluating the voice clarity of the conference room 1 using the first voice data and the second voice data, the information processing device 10 converts each of the first voice data and the second voice data into text data and compares the converted text data to evaluate the voice clarity of the conference room 1. By evaluating the voice clarity of the conference room 1 by comparing the text data, the information processing device 10 can quantitatively evaluate whether the voices picked up in the conference room 1 can be heard accurately.

[0019] FIG. 2 is a block diagram showing the hardware configuration of the information processing device 10. As shown in FIG.

[0020] 2, the information processing device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to each other via a bus 19 so as to be able to communicate with each other.

[0021] CPU 11 is a central processing unit that executes various programs and controls each component. That is, CPU 11 reads programs from ROM 12 or storage 14 and executes the programs using RAM 13 as a work area. CPU 11 controls the above components and performs various arithmetic processing in accordance with the programs recorded in ROM 12 or storage 14. In this embodiment, ROM 12 or storage 14 stores an information processing program that evaluates whether voices picked up in conference room 1 can be heard accurately.

[0022] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores programs or data as a working area. The storage 14 is configured with a storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory, and stores various programs including the operating system and various data.

[0023] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various inputs.

[0024] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may also function as the input unit 15 by adopting a touch panel system.

[0025] The communication interface 17 is an interface for communicating with other devices such as the personal computer 2, and uses standards such as Ethernet (registered trademark), FDDI, and Wi-Fi (registered trademark).

[0026] When executing the above information processing program, the information processing device 10 uses the above hardware resources to realize various functions. The functional configuration realized by the information processing device 10 will be described.

[0027] FIG. 3 is a block diagram showing an example of the functional configuration of the information processing device 10. As shown in FIG.

[0028] 3, the information processing device 10 has, as functional components, an acquisition unit 101, a generation unit 102, and an evaluation unit 103. Each functional component is realized by the CPU 11 reading and executing an information processing program stored in the ROM 12 or the storage 14.

[0029] The acquisition unit 101 acquires the first voice data and the second voice data used for evaluating the voice clarity of the conference room 1 from the personal computer 2. The first voice data and the second voice data acquired by the acquisition unit 101 are recorded in the storage 14.

[0030] The generation unit 102 generates first text data and second text data based on the first voice data and second voice data acquired by the acquisition unit 101. The generation unit 102 generates the first text data and second text data from the first voice data and second voice data using an arbitrary conversion program. For example, the generation unit 102 may generate the first text data and second text data from the first voice data and second voice data using a transcription function included in software used in an online conference between the personal computer 2 in the conference room 1 and the information processing device 10.

[0031] The evaluation unit 103 evaluates the speech clarity of the conference room 1 based on the first speech data and the second speech data acquired by the acquisition unit 101. Specifically, the evaluation unit 103 evaluates the speech clarity of the conference room 1 using the first text data and the second text data generated by the generation unit 102. More specifically, the evaluation unit 103 evaluates the speech clarity of the conference room 1 based on the matching rate between the first text data and the second text data. The evaluation unit 103 may directly use the matching rate between the first text data and the second text data as the speech clarity of the conference room 1, or may evaluate the speech clarity of the conference room 1 by comparing the matching rate between the first text data and the second text data with a threshold. For example, the evaluation unit 103 may evaluate the speech clarity of the conference room 1 as 5 if the matching rate is 80 percent or more, as 4 if the matching rate is 60 percent or more but less than 80 percent, as 3 if the matching rate is 40 percent or more but less than 60 percent, as 2 if the matching rate is 20 percent or more but less than 40 percent, and as 1 if the matching rate is less than 20 percent. Of course, the setting of the threshold is not limited to this example.

[0032] The evaluation unit 103 may also divide the first text data and the second text data into phrases, calculate the number of phrases in which speech is incorrectly recognized or phrases in which speech cannot be identified (these are referred to as erroneous phrases) for each phrase, and calculate an average transcription accuracy rate for the second text data from an average erroneous phrase, which is the average number of erroneous phrases for a plurality of second text data, thereby evaluating the speech clarity of the conference room 1. The evaluation unit 103 may use the average transcription accuracy rate as the speech clarity of the conference room 1 directly, or may evaluate the speech clarity of the conference room 1 by comparing the average transcription accuracy rate with a threshold. For example, the evaluation unit 103 may evaluate the speech clarity as 5 if the average transcription accuracy rate is 80 percent or more, 4 if the average transcription accuracy rate is 60 percent or more and less than 80 percent, 3 if the average transcription accuracy rate is 40 percent or more and less than 60 percent, 2 if the average transcription accuracy rate is 20 percent or more and less than 40 percent, and 1 if the average transcription accuracy rate is less than 20 percent. Of course, the setting of the threshold value is not limited to this example.

[0033] The information processing device 10 according to this embodiment has such a configuration, and thus can quantitatively evaluate the voice clarity in the conference room 1.

[0034] An example of an evaluation of speech clarity in the conference room 1 by the information processing device 10 according to this embodiment is shown below. Table 1 shows an example of an evaluation of speech clarity in the conference room 1 by the information processing device 10. Table 1 shows examples of the information processing device 10 evaluating speech clarity in the conference room 1 when no sound-absorbing material is used in the conference room 1, when sound-absorbing material is used on one side, and when sound-absorbing material is used on two side surfaces. Table 1 also shows the average erroneous phrases and the average transcription accuracy rate of the second text data when the phrases are divided into 54 segments.

[0035] [Table 1]

[0036] As shown in Table 1, when no sound-absorbing material was used in Conference Room 1, the average number of incorrect phrases was 25.4 and the average transcription accuracy rate was 53%. In contrast, when sound-absorbing material was used on one side of Conference Room 1, the average number of incorrect phrases was 11.4 and the average transcription accuracy rate was 79%. Furthermore, when sound-absorbing material was used on two sides of Conference Room 1, the average number of incorrect phrases was 2.5 and the average transcription accuracy rate was 95%.

[0037] As described above, it can be seen that taking measures to improve the quality of the sound picked up in the conference room 1 reduces the average number of erroneous phrases and improves the average transcription accuracy rate. Therefore, the information processing device 10 according to this embodiment can quantitatively evaluate the speech clarity of the conference room 1.

[0038] Next, the operation of the information processing device 10 will be described.

[0039] 4 is a flowchart showing the flow of information processing by the information processing device 10. The CPU 11 reads out an information processing program from the ROM 12 or the storage 14, loads it into the RAM 13, and executes it, thereby performing information processing.

[0040] In step S101, the CPU 11 acquires from the personal computer 2 the first voice data and the second voice data used to evaluate the voice clarity of the conference room 1.

[0041] Following step S101, in step S102, the CPU 11 generates first text data and second text data based on the first voice data and second voice data acquired in step S101, respectively. The CPU 11 generates the first text data and second text data from the first voice data and second voice data using an arbitrary conversion program.

[0042] Following step S102, in step S103, the CPU 11 evaluates the voice clarity of the conference room 1 based on the first voice data and the second voice data acquired in step S101. Specifically, the CPU 11 evaluates the voice clarity of the conference room 1 using the first text data and the second text data generated in step S102. More specifically, the CPU 11 evaluates the voice clarity of the conference room 1 based on the matching rate between the first text data and the second text data generated in step S102.

[0043] The information processing device 10 according to the present embodiment can quantitatively evaluate the voice clarity in the conference room 1 by executing such processing.

[0044] Although the embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person skilled in the art of the present disclosure can conceive of various modifications or alterations within the scope of the technical idea described in the claims, and it is understood that these modifications or alterations also naturally fall within the technical scope of the present disclosure.

[0045] Furthermore, the effects described in the above embodiments are explanatory or exemplary and are not limited to those described in the above embodiments. In other words, the technology according to the present disclosure may achieve other effects that are obvious to a person skilled in the art of the present disclosure from the description in the above embodiments, in addition to or instead of the effects described in the above embodiments.

[0046] In the above embodiments, the information processing performed by the CPU after reading the software (program) may be performed by various processors other than the CPU. Examples of such processors include programmable logic devices (PLDs) whose circuit configuration can be changed after fabrication, such as field-programmable gate arrays (FPGAs), and dedicated electrical circuits, such as application-specific integrated circuits (ASICs), which are processors with circuit configurations specifically designed to perform specific processing. The information processing may be performed by one of these processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0047] In addition, in each of the above embodiments, the information processing program is described as being pre-stored (installed) in a ROM or storage, but this is not limiting. The program may be provided in a form recorded on a non-transitory recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The program may also be downloaded from an external device via a network. [Explanation of symbols]

[0048] 1 Conference Room 2. Personal Computers 3 Network 4 speakers 5. Microphone 10. Information processing equipment 101 Acquisition Department 102 Generation part 103 Evaluation Department

Claims

1. a generation unit that generates first text data from first voice data and generates second text data from second voice data obtained by collecting sound derived from the first voice data; an evaluation unit that evaluates the voice clarity of the environment in which the second voice data is collected by using the first text data and the second text data; An information processing device comprising:

2. The information processing device according to claim 1 , wherein the evaluation unit evaluates the speech clarity using a matching rate between the first text data and the second text data.

3. The information processing device according to claim 2 , wherein the evaluation unit evaluates the speech clarity using a matching rate for each phrase between the first text data and the second text data.

4. 4. The information processing device according to claim 1, wherein the first audio data is audio data that is not affected by the environment.

5. The information processing device according to claim 4 , wherein the first voice data is voice data acquired through a network.

6. The processor: generating first text data from first voice data, and generating second text data from second voice data obtained by collecting sound derived from the first voice data; Using the first text data and the second text data, the voice clarity of the environment in which the second voice data is collected is evaluated. A method for processing information.

7. On the computer, generating first text data from first voice data, and generating second text data from second voice data obtained by collecting sound derived from the first voice data; Using the first text data and the second text data, the voice clarity of the environment in which the second voice data is collected is evaluated. An information processing program that executes processing.

Images