Speech recognition device, speech recognition method, and program

Abstract

To smoothly playback data output from external devices.SOLUTION: A voice recognition device (1) comprises a transmitter (11) and a voice recognition unit (14) that performs voice recognition processing on the user's voice. The transmitter (11) transmits a signal to stop playing stored contents to an external device (4) that plays stored contents and outputs external sound when the voice recognition processing is performed by the voice recognition unit (14).SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a speech recognition device, a speech recognition method, and a program.

Background Art

[0002] There is disclosed a technology for stopping and resuming data playback in response to a voice command from a user in an apparatus that plays back data such as content. For example, Patent Document 1 describes a data voice playback apparatus that recognizes a voice command from a user, and pauses and resumes the text-to-speech playback of text data or HTML data in accordance with the recognized command content.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When the above-described data voice playback apparatus is adopted as an apparatus that plays back data output from an external device that plays back content (for example, a hard disk recorder, a Blu-ray (registered trademark) player, etc.), a problem arises in that the above-described data voice playback apparatus cannot smoothly play back the data output from the external device.

[0005] Specifically, the aforementioned data audio playback device needs to continue storing the data output from the external device within its own system during the pause period when playback is paused in response to a user's voice command. In this configuration, if the pause period is long, the storage capacity within the device may become insufficient. When the storage capacity becomes insufficient, problems arise such as being unable to resume playback from where it was paused, or data that could not be stored being lost, resulting in the inability to smoothly play back the data output from the external device.

[0006] One aspect of the present invention has been made in view of the above-mentioned problems, and its purpose is to provide a technology for smoothly reproducing data output from an external device. [Means for solving the problem]

[0007] To solve the above problems, a speech recognition device according to one aspect of the present invention is a speech recognition device comprising a transmitting unit and a speech recognition unit that performs speech recognition processing on the user's voice, wherein the transmitting unit transmits a signal to an external device that plays stored content and outputs external audio to stop playback of the stored content when speech recognition processing is performed by the speech recognition unit.

[0008] To solve the above problems, a speech recognition method according to one aspect of the present invention is a speech recognition method comprising a transmission step and a speech recognition step of performing speech recognition processing on a user's voice, wherein the transmission step includes a step of transmitting a signal to an external device that plays stored content and outputs external audio, to stop playback of the stored content, triggered by the performance of the speech recognition processing in the speech recognition step.

[0009] To solve the above problems, a program according to one aspect of the present invention is a program for causing a computer to function as a speech recognition device, wherein the program causes the computer to function as a transmitting unit and a speech recognition unit that performs speech recognition processing on the user's voice, and the transmitting unit, triggered by the speech recognition unit performing speech recognition processing, transmits a signal to an external device that plays stored content and outputs external audio to stop playing the stored content. [Effects of the Invention]

[0010] According to one aspect of the present invention, data output from an external device can be smoothly reproduced. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram showing the configuration of a voice output system equipped with a voice recognition device according to Embodiment 1 of the present invention. [Figure 2] This is a schematic diagram showing the state of speech recognition by the speech recognition device according to Embodiment 1 of the present invention. [Figure 3] This is a schematic diagram showing the speech recognition device according to Embodiment 1 of the present invention performing speech recognition and the state at the end of the speech recognition process. [Figure 4] This flowchart shows the processing flow performed by the speech recognition device according to Embodiment 1 of the present invention. [Figure 5] This figure shows the data flow in an audio output system according to Embodiment 1 of the present invention. [Figure 6] This figure shows the data flow in an audio output system according to Embodiment 1 of the present invention. [Figure 7] This figure shows the data flow in an audio output system according to Embodiment 1 of the present invention. [Figure 8] This figure shows the data flow in an audio output system according to Embodiment 1 of the present invention. [Figure 9]FIG. 2 is a block diagram showing the configuration of a voice output system including the voice recognition device according to Embodiment 2 of the present invention. [Figure 10] FIG. 3 is a schematic diagram showing a state at the start of voice recognition by the voice recognition device according to Embodiment 2 of the present invention. [Figure 11] FIG. 4 is a schematic diagram showing a state in which the voice recognition device according to Embodiment 2 of the present invention is executing voice recognition and a state at the end of the voice recognition processing. [Figure 12] FIG. 5 is a flowchart showing the flow of processing executed by the voice recognition device according to Embodiment 2 of the present invention. [Mode for Carrying Out the Invention]

[0012] [Embodiment 1] Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings.

[0013] (Voice Output System 100) FIG. 1 is a block diagram showing the configuration of a voice output system 100 including a voice recognition device 1 according to the present embodiment. As shown in FIG. 1, the voice output system 100 includes the voice recognition device 1, a speaker 2, a microphone 3, and an external device 4. In the present embodiment, a television receiver is given as an example of the voice recognition device 1. In addition, a hard disk recorder is given as an example of the external device 4.

[0014] In the voice output system 100, the external device 4 outputs the voice in the stored content as external voice by playing the stored content. When acquiring the external voice output from the external device 4, the voice recognition device 1 outputs the external voice via the speaker 2. Hereinafter, the processing in which the voice recognition device 1 outputs the external voice via the speaker 2 is also expressed as "playing the external voice".

[0015] Further, in the audio output system 100, the speech recognition apparatus 1 recognizes a user's speech acquired via the microphone 3, and performs processing according to the recognition result. The speech recognition apparatus 1 is configured to stop output of external audio in response to execution of the user's speech recognition processing.

[0016] It should be noted that the speaker 2 and the microphone 3 may be components provided in the speech recognition apparatus 1.

[0017] Here, in the audio output system 100, in addition to the configuration in which the speech recognition apparatus 1 outputs the external audio output from the external device 4, the speech recognition apparatus 1 may acquire an external image output from the external device 4, and the speech recognition apparatus 1 may be configured to display the acquired external image. In other words, in the audio output system 100, the speech recognition apparatus 1 may be configured to acquire an image and audio in the stored content reproduced by the external device 4 as an external image and external audio respectively, and output the acquired external image and external audio. Also in this configuration, display of the external image may be stopped in response to execution of the user's speech recognition processing.

[0018] (Speech Recognition Apparatus 1) As shown in FIG. 1, the speech recognition apparatus 1 includes an apparatus control unit 10 and an apparatus input / output unit 15.

[0019] The apparatus input / output unit 15 is an interface that outputs data supplied from the apparatus control unit 10 to the external device 4, and supplies data output from the external device 4 to the apparatus control unit 10. An example of the interface standard for data input and output by the apparatus input / output unit 15 is HDMI (High-Definition Multimedia Interface, registered trademark).

[0020] The apparatus control unit 10 comprehensively controls each component included in the speech recognition apparatus 1. The apparatus control unit 10 includes a transmission unit 11, an acquisition unit 12 (external audio acquisition unit), an audio processing unit 13, and a speech recognition unit 14.

[0021] The transmitting unit 11 transmits a signal to the external device 4 via the device input / output unit 15. An example of a signal transmitted by the transmitting unit 11 is a signal that, triggered by speech recognition processing by the speech recognition unit 14, causes the external device 4, which plays the stored content and outputs external audio, to stop playing the stored content.

[0022] Another example of a signal transmitted by the transmitting unit 11 is a signal sent to the external device 4 to release the stopped state of playback of the stored content, triggered by the completion of speech recognition processing by the speech recognition unit 14.

[0023] Furthermore, an example of a signal transmitted by the transmission unit 11 to stop playback of stored content and a signal to release the stopped state of playback of stored content is CEC (Consumer Electronics Control).

[0024] The acquisition unit 12 acquires external audio output from the external device 4 via the device input / output unit 15. The acquisition unit 12 supplies the acquired external audio to the audio processing unit 13.

[0025] The audio processing unit 13 processes the acquired audio and outputs it to the speaker 2. Examples of audio acquired by the audio processing unit 13 include external audio and user audio, which represents audio spoken by the user.

[0026] The speech recognition unit 14 acquires user voice via the microphone 3. The speech recognition unit 14 also performs speech recognition processing on the user voice. The speech recognition unit 14 then executes processing according to the recognition result obtained through the speech recognition processing.

[0027] The speech recognition processing performed by the speech recognition unit 14 on user speech is carried out using known methods. One example of the speech recognition processing performed by the speech recognition unit 14 is a method that uses a speech recognition model that takes speech as input and outputs text data of that speech.

[0028] (External device 4) As shown in Figure 1, the external device 4 comprises a device control unit 40, a device input / output unit 41, and a storage unit 42.

[0029] The device control unit 40 comprehensively controls each component of the external device 4.

[0030] The device input / output unit 41 is an interface that outputs data supplied from the device control unit 40 to the voice recognition device 1, and supplies data output from the voice recognition device 1 to the device control unit 40. HDMI is an example of an interface standard for which the device input / output unit 41 inputs and outputs data.

[0031] The memory unit 42 is a storage device that stores data. An example of data stored in the memory unit 42 is the stored content.

[0032] (Overview of processing in the audio output system 100) The processing overview in the voice output system 100 will be explained using Figures 2 and 3. Figure 2 is a schematic diagram showing the state at the start of voice recognition by the voice recognition device 1. Figure 3 is a schematic diagram showing the state of the voice recognition device 1 performing voice recognition and the state at the end of the voice recognition process.

[0033] As shown on the left side of Figure 2, the speech recognition device 1 outputs external audio from the external device 4 while the external device 4 is playing the stored content.

[0034] Next, when the user speaks, the speech recognition device 1 acquires the user's voice and performs speech recognition processing, as shown on the right side of Figure 2. Here, the speech recognition device 1 may be configured to perform speech recognition processing when it acquires a predetermined voice from the user (for example, a hotword that instructs the start of the execution of speech recognition processing).

[0035] Furthermore, as shown on the right side of Figure 2, the speech recognition device 1 outputs a signal to the external device 4 to stop playback of the stored content when speech recognition processing is performed.

[0036] Next, the speech recognition device 1 performs speech recognition processing on the user's voice. Then, as shown on the left side of Figure 3, the speech recognition device 1 performs processing according to the recognition result. On the left side of Figure 3, since the recognition result is the question "What's the weather like in XX?", the speech recognition device 1 outputs the answer to the question, "What's the weather like in XX?", as voice. The speech recognition device 1 may also be configured to display the answer to the question.

[0037] Next, as shown on the right side of Figure 3, the speech recognition device 1, upon completion of the speech recognition process, sends a signal to the external device 4 to release the stopped playback state of the stored content. Upon receiving the signal to release the stopped playback state of the stored content, the external device 4 resumes playback of the stored content and outputs external audio to the speech recognition device 1. The speech recognition device 1 acquires the external audio from the external device 4 and outputs the acquired external audio.

[0038] Thus, speech recognition processing refers to the process from when the speech recognition device 1 recognizes speech to when it executes processing according to the recognition result. The speech recognition device 1 may be configured to terminate the speech recognition processing if it does not acquire user speech for a predetermined period (for example, 3 seconds, 5 seconds) after executing processing according to the recognition result.

[0039] Thus, since the speech recognition device 1 does not acquire data output from the external device 4 during speech recognition processing, it does not need to store the data output from the external device 4. Therefore, the speech recognition device 1 can prevent data from being lost due to insufficient memory capacity, and can smoothly play back the data output from the external device.

[0040] (Processing performed by speech recognition device 1) Figure 4 is a flowchart showing the processing flow performed by the speech recognition device 1. Figures 5 to 8 are diagrams showing the data flow in the speech output system 100, respectively. The processing performed by the speech recognition device 1 will be explained with reference to Figures 5 to 8.

[0041] (Step S10) In step S10, the voice processing unit 13 of the voice recognition device 1 outputs external audio output from the external device 4 via the speaker 2.

[0042] The data flow in step S10 will be explained with reference to Figure 5.

[0043] The device control unit 40 of the external device 4 plays back the stored content stored in the memory unit 42. The device control unit 40 then outputs the audio from the stored content as external audio to the speech recognition device 1 via the device input / output unit 41.

[0044] The acquisition unit 12 of the speech recognition device 1 acquires external audio from an external device 4 via the device input / output unit 15. The acquisition unit 12 supplies the acquired external audio to the speech processing unit 13. The speech processing unit 13 outputs the acquired external audio to the speaker 2.

[0045] (Step S11) In step S11, the speech recognition unit 14 determines whether or not it has detected a speech recognition trigger via the microphone 3. Examples of how the speech recognition unit 14 determines whether or not it has detected a speech recognition trigger include whether or not it has acquired voice from the user, and whether or not it has acquired predetermined voice from the user.

[0046] If the result of the determination in step S11 is "NO", that is, if the speech recognition unit 14 has not detected a speech recognition trigger, the speech recognition device 1 will execute the process of step S11 again.

[0047] (Step S12) If the result of the determination in step S11 is "YES," that is, if the speech recognition unit 14 detects a speech recognition trigger, in step S12 the acquisition unit 12 determines whether or not it is acquiring external audio from the external device 4.

[0048] (Step S13) If the determination result in step S12 is "YES," that is, if the acquisition unit 12 is acquiring external audio from the external device 4, in step S13, the transmission unit 11 sends a signal to the external device 4 to stop playback of the stored content.

[0049] The data flow in steps S11 to S13 will be explained with reference to Figure 6.

[0050] When the voice recognition unit 14 detects a voice recognition trigger via the microphone, the transmission unit 11 transmits a signal to the external device 4 via the device input / output unit 15 to stop playback of the stored content. The device control unit 40 of the external device 4 receives the signal to stop playback of the stored content via the device input / output unit 41. Upon receiving the signal to stop playback of the stored content, the device control unit 40 stops playback of the stored content stored in the storage unit 42. In other words, upon receiving the signal to stop playback of the stored content, the device control unit 40 stops outputting external audio.

[0051] (Step S14) If the result of the determination in step S12 is "NO", that is, if the acquisition unit 12 has not acquired external audio from the external device 4, and after executing step S13, in step S14 the speech recognition unit 14 determines whether or not it has finished speech recognition.

[0052] If the result of the determination in step S14 is "NO," that is, if the speech recognition unit 14 has not finished speech recognition, the speech recognition device 1 will execute the process in step S13 again.

[0053] If the speech recognition unit 14 has not yet finished speech recognition, in other words, if the speech recognition unit 14 is executing speech recognition processing and performing processing according to the recognition result, the data flow during the period in which such processing is being performed will be explained with reference to Figure 7.

[0054] The speech recognition unit 14 of the speech recognition device 1 acquires user voice via the microphone 3. The device control unit 10 then outputs the user voice via the speaker 2 through the voice processing unit 13.

[0055] (Step S15) If the determination result in step S14 is "YES," that is, if the speech recognition unit 14 has finished speech recognition, in step S15 the acquisition unit 12 determines whether or not it has stopped acquiring external audio from the external device 4.

[0056] If the determination result in step S15 is "NO," that is, if the acquisition unit 12 has not stopped acquiring external audio from the external device 4, the speech recognition device 1 terminates the process shown in Figure 4.

[0057] (Step S16) If the determination result in step S15 is "YES," that is, if the acquisition unit 12 has stopped acquiring external audio from the external device 4, the transmission unit 11 sends a signal to the external device 4 to release the stopped state of playback of the stored content.

[0058] The data flow in step S16 will be explained with reference to Figure 8.

[0059] If the acquisition unit 12 has stopped acquiring external audio from the external device 4, the transmission unit 11 sends a signal to the external device 4 to release the stopped state of playback of the stored content.

[0060] Then, the device control unit 40 of the external device 4 plays back the stored content stored in the memory unit 42. Subsequently, the device control unit 40 outputs the audio from the stored content as external audio to the voice recognition device 1 via the device input / output unit 41.

[0061] The acquisition unit 12 of the speech recognition device 1 acquires external audio from an external device 4 via the device input / output unit 15. The acquisition unit 12 supplies the acquired external audio to the speech processing unit 13. The speech processing unit 13 outputs the acquired external audio to the speaker 2.

[0062] Thus, according to the audio output system 100 of this embodiment, the speech recognition device 1 transmits a signal to the external device 4 to stop playback of the stored content when speech recognition processing is performed. Therefore, according to the audio output system 100 of this embodiment, the speech recognition device 1, which plays back data output from the external device 4, does not acquire data output from the external device 4 during speech recognition processing, and thus does not need to store the data output from the external device 4. Consequently, the speech recognition device 1 can prevent data output from the external device 4 from being lost due to insufficient storage capacity, and can play back the data output from the external device smoothly.

[0063] Furthermore, according to the audio output system 100 of this embodiment, the speech recognition device 1 transmits a signal to the external device 4 to release the stopped state of playback of the stored content when the speech recognition process is completed. Therefore, since the speech recognition device 1 acquires the data output from the external device 4 again after the speech recognition process is completed, the data output from the external device can be played back smoothly.

[0064] Furthermore, the speech recognition device 1 does not need to acquire data output from the external device 4 while speech recognition processing is in progress. Therefore, the speech recognition device 1 does not need to perform speech recognition processing and data acquisition processing from the external device 4 in parallel, thus preventing a decrease in the accuracy of speech recognition.

[0065] [Embodiment 2] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0066] Figure 9 is a block diagram showing the configuration of an audio output system 100a equipped with an audio recognition device 1a according to this embodiment. As shown in Figure 9, the audio output system 100a comprises an audio recognition device 1a, a speaker 2, a microphone 3, and an external device 4a. In this embodiment, the external device 4a can be, for example, a smartphone or a music player.

[0067] In the voice output system 100a, the voice recognition device 1a and the external device 4a are connected by wireless communication. In this embodiment, a configuration in which the voice recognition device 1a and the external device 4a are connected by Bluetooth® is described, but is not limited to this. The wireless communication standard between the voice recognition device 1a and the external device 4a is one that allows the voice recognition device 1a to stop playback of stored content and to release the stopped state of playback of stored content by transmitting a signal to the external device 4a. The other configurations are the same as those of the voice output system 100 described in Embodiment 1, so a detailed explanation is omitted.

[0068] (Voice recognition device 1a) As shown in Figure 9, the speech recognition device 1a comprises a device control unit 10a and a device input / output unit 15a.

[0069] The device input / output unit 15a is an interface that outputs data supplied from the device control unit 10a to an external device 4a, and supplies data output from the external device 4a to the device control unit 10a.

[0070] The device control unit 10a comprehensively controls each component of the speech recognition device 1a. The device control unit 10a includes a transmission unit 11a, an acquisition unit 12a (external voice acquisition unit), a voice processing unit 13, and a speech recognition unit 14.

[0071] The transmitting unit 11a transmits a signal to the external device 4a via the device input / output unit 15a.

[0072] One example of a signal transmitted by the transmitting unit 11a is a signal that, triggered by speech recognition processing performed by the speech recognition unit 14, causes an external device 4a, which plays the stored content and outputs external audio, to stop playing the stored content.

[0073] Another example of a signal transmitted by the transmitting unit 11a is a signal sent to the external device 4a to release the stopped state of playback of the stored content, triggered by the completion of speech recognition processing by the speech recognition unit 14.

[0074] Furthermore, as an example of a signal transmitted by the transmission unit 11a to stop playback of stored content and a signal to release the stopped state of playback of stored content, a signal using AVRCP (Audio Video Remote Control Profile) can be cited.

[0075] The acquisition unit 12a acquires external audio output from the external device 4a via the device input / output unit 15a. The acquisition unit 12a supplies the acquired external audio to the audio processing unit 13.

[0076] The voice processing unit 13 and the voice recognition unit 14 are as described above.

[0077] (External device 4a) As shown in Figure 9, the external device 4a comprises a device control unit 40a, a device input / output unit 41a, and a storage unit 42.

[0078] The device control unit 40a comprehensively controls each component of the external device 4a.

[0079] The device input / output unit 41a is an interface that outputs data supplied from the device control unit 40a to the speech recognition device 1a, and supplies data output from the speech recognition device 1a to the device control unit 40a.

[0080] The memory unit 42 is as described above.

[0081] (Overview of processing in the audio output system 100a) The processing overview in the voice output system 100a will be explained using Figures 10 and 11. Figure 10 is a schematic diagram showing the state at the start of voice recognition by the voice recognition device 1a. Figure 11 is a schematic diagram showing the state of the voice recognition device 1a performing voice recognition and the state at the end of the voice recognition process.

[0082] Similar to the embodiment described above, the speech recognition device 1a outputs external audio from the external device 4a while the external device 4a is playing the stored content, as shown on the left side of Figure 10. Then, as shown on the right side of Figure 10, the speech recognition device 1a acquires the user's voice and, triggered by the speech recognition process, outputs a signal to the external device 4a to stop playing the stored content.

[0083] Furthermore, similar to the embodiment described above, the speech recognition device 1a performs processing according to the recognition result, as shown on the left side of Figure 3. Then, upon completion of the speech recognition process, the speech recognition device 1a sends a signal to the external device 4a to release the stopped state of playback of the stored content. When the external device 4a receives the signal to release the stopped state of playback of the stored content, it resumes playback of the stored content.

[0084] Thus, even when the speech recognition device 1a is connected to the external device 4a via wireless communication, it does not acquire data output from the external device 4a during speech recognition processing, and therefore does not need to store the data output from the external device 4a. Consequently, the speech recognition device 1a can prevent data from being lost due to insufficient memory capacity, and can smoothly play back the data output from the external device.

[0085] (Processing performed by speech recognition device 1a) Figure 12 is a flowchart showing the processing flow performed by the speech recognition device 1a. The processing performed by the speech recognition device 1a will be explained with reference to Figure 12.

[0086] (Step S20) In step S20, the voice processing unit 13 of the voice recognition device 1a outputs external audio output from the external device 4a via the speaker 2.

[0087] (Step S21) In step S21, the voice recognition unit 14 determines whether or not it has detected a voice recognition trigger via the microphone 3.

[0088] If the result of the determination in step S21 is "NO", that is, if the speech recognition unit 14 has not detected a speech recognition trigger, the speech recognition device 1a will execute the process of step S21 again.

[0089] (Step S22) If the determination result in step S21 is "YES," that is, if the voice recognition unit 14 detects a voice recognition trigger, in step S22, the acquisition unit 12a determines whether or not external audio is being acquired from the external device 4a via Bluetooth.

[0090] (Step S23) If the determination result in step S22 is "YES", that is, if the acquisition unit 12a is acquiring external audio from the external device 4a via Bluetooth, in step S23, the transmission unit 11a sends a signal to the external device 4a via Bluetooth to stop playback of the stored content.

[0091] (Step S24) If the result of the determination in step S22 is "NO", that is, if the acquisition unit 12a has not acquired external audio from the external device 4a via Bluetooth, and after executing step S23, in step S24 the voice recognition unit 14 determines whether or not voice recognition has ended.

[0092] If the result of the determination in step S24 is "NO", that is, if the speech recognition unit 14 has not finished speech recognition, the speech recognition device 1a will execute the process in step S23 again.

[0093] (Step S25) If the result of the determination in step S24 is "YES", that is, if the speech recognition unit 14 has finished speech recognition, in step S25 the acquisition unit 12a determines whether or not it has stopped acquiring external audio from the external device 4a.

[0094] If the determination result in step S15 is "NO," that is, if the acquisition unit 12a has not stopped acquiring external audio from the external device 4a, the speech recognition device 1a terminates the process shown in Figure 4.

[0095] (Step S26) If the determination result in step S15 is "YES," that is, if the acquisition unit 12a has stopped acquiring external audio from the external device 4a, the transmission unit 11a sends a signal to the external device 4a via Bluetooth to release the stopped state of playback of the stored content.

[0096] Thus, according to the voice output system 100a of this embodiment, even if the voice recognition device 1a and the external device 4a are communicating wirelessly (via Bluetooth), a signal is sent to the external device 4a to stop playback of the stored content when voice recognition processing is performed. Therefore, according to the voice output system 100a of this embodiment, the voice recognition device 1a, which plays back the data output from the external device 4a, does not acquire the data output from the external device 4a during voice recognition processing, and thus does not need to store the data output from the external device 4a.

[0097] Furthermore, according to the voice output system 100 of this embodiment, even if the voice recognition device 1a and the external device 4a are communicating wirelessly (via Bluetooth), the voice recognition device 1a sends a signal to the external device 4a to release the stopped state of playback of the stored content when the voice recognition process is completed. Therefore, after the voice recognition process is completed, the voice recognition device 1a acquires the data output from the external device 4a again, enabling smooth playback of the data output from the external device. Therefore, the speech recognition device 1a can smoothly reproduce data output from an external device. Furthermore, since the speech recognition device 1a does not need to perform speech recognition processing and data acquisition processing from the external device 4a in parallel, it can prevent a decrease in the accuracy of speech recognition.

[0098] [Examples of implementation using software] The functions of the speech recognition devices 1 and 1a (hereinafter referred to as "devices") can be realized by programs that cause a computer to function as the device, and which cause a computer to function as each control block of the device (in particular, each part included in the device control units 10 and 10a).

[0099] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the program. By executing the program using this control device and storage device, the functions described in each of the embodiments are realized.

[0100] The above program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the above device. In the latter case, the program may be supplied to the above device via any wired or wireless transmission medium.

[0101] Furthermore, some or all of the functions of each of the above control blocks can also be realized by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the above control blocks are formed is also included in the scope of the present invention. In addition, it is also possible to realize the functions of each of the above control blocks by, for example, a quantum computer.

[0102] 〔summary〕 A speech recognition device (1, 1a) according to aspect 1 of the present invention comprises a transmitting unit (11) and a speech recognition unit (14) that performs speech recognition processing on the user's voice, wherein the transmitting unit (11) transmits a signal to an external device (4, 4a) that plays stored content and outputs external audio, to stop playback of the stored content, triggered by speech recognition processing being performed by the speech recognition unit (14).

[0103] According to the above configuration, the speech recognition device sends a signal to the external device to stop playback of the stored content when speech recognition processing is performed. Therefore, the speech recognition device that plays back data output from the external device does not acquire data output from the external device during speech recognition processing, and thus does not need to store the data output from the external device. Consequently, the speech recognition device can prevent data from being lost due to insufficient storage capacity, and can play back the data output from the external device smoothly.

[0104] In the speech recognition device (1, 1a) according to aspect 2 of the present invention, in aspect 1, the transmitting unit (11) may, upon completion of speech recognition processing by the speech recognition unit (14), transmit a signal to the external device (4, 4a) to release the stopped state of playback of the stored content.

[0105] According to the above configuration, the speech recognition device sends a signal to the external device to release the stopped state of playback of the stored content when the speech recognition process is completed. Therefore, after the speech recognition process is completed, the speech recognition device acquires data output from the external device again, and can smoothly play back the data output from the external device.

[0106] The voice recognition device (1, 1a) according to embodiment 3 of the present invention may further include, in embodiment 1 or 2 above, a microphone (3) for acquiring the user's voice, an external voice acquisition unit (acquisition unit 12, 12a) for acquiring external voice output from an external device, and a speaker (2) for outputting the external voice acquired by the external voice acquisition unit (acquisition unit 12, 12a).

[0107] With the above configuration, the speech recognition device can acquire the user's voice within its own device. Furthermore, the speech recognition device can function as an audio output device that outputs external audio from an external device.

[0108] A speech recognition method according to aspect 4 of the present invention is a speech recognition method comprising a transmission step and a speech recognition step of performing speech recognition processing on a user's voice, wherein the transmission step includes a step of transmitting a signal to an external device (4, 4a) that plays stored content and outputs external audio, to stop playback of the stored content, triggered by the performance of speech recognition processing in the speech recognition step.

[0109] The above configuration produces the same effects as in the first embodiment.

[0110] A program according to aspect 5 of the present invention is a program for causing a computer to function as a speech recognition device (1, 1a), wherein the program causes the computer to function as a transmitting unit (11) and a speech recognition unit that performs speech recognition processing (14) on the user's voice, and the transmitting unit (11), triggered by the speech recognition unit (14) performing speech recognition processing, transmits a signal to an external device (4, 4a) that plays stored content and outputs external audio to stop playing the stored content.

[0111] The above configuration produces the same effects as in the first embodiment.

[0112] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment. [Explanation of symbols]

[0113] 100, 100a audio output system 1, 1a Speech recognition device 10, 10a Device control unit 11, 11a Transmitter 12, 12a Acquisition unit (external audio acquisition unit) 13. Audio Processing Unit 14. Voice Recognition Unit 4, 4a External equipment 40, 40a Equipment control unit 41, 41a Equipment input / output section 42 Storage section

Claims

1. The transmitting unit, A speech recognition unit that performs speech recognition processing on the user's voice, A microphone that acquires the user's voice, An external audio acquisition unit that acquires external audio data, which is data output by an external device, A speech recognition device comprising a speaker that outputs external audio acquired by the external audio acquisition unit, If the voice recognition unit determines that the recognition result is a question from the user, it will output the answer to that question in voice. The transmitting unit, triggered by the speech recognition unit performing speech recognition processing, transmits a signal to the external device that plays the stored content and outputs the external audio to stop playback of the stored content. The transmitting unit, upon completion of the speech recognition process including the output of the response, transmits a signal to the external device to release the stopped state of playback of the stored content. A speech recognition device characterized by the following features.

2. A speech recognition device equipped with a microphone that acquires the user's voice and a speaker that outputs external audio data, Sending step, An external audio acquisition step that acquires the external audio output from an external device, A speech recognition method that performs a speech recognition step of performing speech recognition processing on the user's voice, In the aforementioned speech recognition step, if the recognition result is a question from the user, the answer to that question is output as speech. The transmission step includes a step in which, triggered by the performance of speech recognition processing in the speech recognition step, a signal is sent to the external device that plays the stored content and outputs the external audio to stop the playback of the stored content. In the transmission step, upon completion of the speech recognition process, including the output of the response, a signal is transmitted to the external device to release the stopped state of playback of the stored content. A speech recognition method characterized by the following features.

3. A program for causing a computer to function as a speech recognition device equipped with a microphone that acquires the user's voice and a speaker that outputs external audio data, The aforementioned program, the computer, The transmitting unit, An external audio acquisition unit that acquires external audio output from an external device, A speech recognition unit performs speech recognition processing on the user's voice, and functions as such. If the voice recognition unit determines that the recognition result is a question from the user, it will output the answer to that question in voice. The transmitting unit, triggered by the speech recognition unit performing speech recognition processing, transmits a signal to the external device that plays the stored content and outputs the external audio to stop playback of the stored content. The transmitting unit, upon completion of the speech recognition processing by the speech recognition unit, including the output of the response, transmits a signal to the external device to release the stopped state of playback of the stored content. program.

Images