JP6922551B2 - Voice processing device, voice processing program, and voice processing method - Google Patents

Description

The present invention relates to a voice processing device, a voice processing program, and a voice processing method, and can be applied to, for example, a call start processing used in a video conferencing system, a conference call system, or the like.

In recent years, there have been increasing opportunities to make calls and communicate with remote locations such as video conferencing and telework using remote communication systems such as video conferencing systems and telephone conferencing systems.

In a remote call system, when connecting to make a call to a remote location, enter and select a contact such as a telephone number on the screen installed in the system, or display the image of the other party displayed on the screen. It is often connected to a remote location by touching it.

Further, Patent Document 1 proposes a communication support robot system in which a remote communication system is incorporated into a robot to support communication between a close relative and a single elderly person.

The communication support robot system described in Patent Document 1 is connected to a call partner and starts a call by touching an image of a close relative or an elderly person displayed on a touch panel display.

Japanese Unexamined Patent Publication No. 2015-184597

However, in the communication support robot system described in Patent Document 1, starting a call by a connection operation such as touching a touch panel display or a connection command is different from an actual face-to-face call, so that there is a sense of presence (face-to-face). The feeling of having a conversation) is very low.

In addition, using the voice recognition system installed in the communication support robot, for example, by calling the name of the other party to be connected, the called voice (hereinafter referred to as the calling voice) is input to the voice recognition system. Even if the connection destination can be determined from the voice recognition result and the connection can be started, the call partner is determined from the voice recognition result after being input to the voice recognition process, and the call partner is connected. , The call voice is not transmitted to the other party. For this reason, the call partner is suddenly connected, and the call partner feels a sense of discomfort or anxiety, and the sense of presence is not improved.

Therefore, in a video conferencing system or the like, when connecting to a call partner by a call voice, a voice processing device that starts a call after transmitting the call voice to the call partner is desired.

The first voice processing device of the present invention is (1) a buffer for reproducing the connection command voice transmitted after connecting to the other side on the other side, and is a buffer for holding an input signal including the above connection command voice for a certain period of time. and parts, and a speech recognition unit which performs speech recognition on (2) the input signal, (3) using the results of the speech recognition unit, the input signal is, the connect command voice determining whether the command determination When the input signal is determined to be the connection command voice by the unit and (4) the command determination unit, the input signal held in the buffer unit is output and held in the buffer unit. It is characterized by having an output switching unit that switches to output the input signal when the voice is output.

The second voice processing program of the present invention is a buffer for (1) playing back the connection command voice transmitted after connecting to the other side of the computer, and the input signal including the above connection command voice is played for a certain period of time. a buffer unit for holding, (2) and a voice recognition unit which performs speech recognition on the input signal, using the (3) results of the speech recognition unit, the input signal is determined whether the connection command voice When the input signal is determined to be the connection command voice by the command determination unit and (4) the command determination unit, the input signal held in the buffer unit is output and held in the buffer unit. It is characterized in that it functions as an output switching unit that switches to output the input signal after outputting the voice.

The third voice processing method of the present invention includes a buffer unit, a voice recognition unit, a command determination unit, and an output switching unit. (1) The buffer unit receives a connection command voice transmitted after connecting to the other party. It is used for reproduction on the side, holds an input signal including the connection command voice for a certain period of time, (2) the voice recognition unit performs voice recognition on the input signal, and (3) the above. command determination unit uses the result of the speech recognition unit, the input signal is judged whether the connection command voice, (4) the output switching unit, the input signal is the connection by the command determination unit When it is determined to be a command voice, the input signal held in the buffer unit is output, and when the voice held in the buffer unit is output, the input signal is switched to be output. And.

According to the present invention, when connecting to a call partner in a video conferencing system or the like, the call voice is transmitted to the call partner, and a state in which the conversation starts from the call voice close to the face-to-face conversation is reproduced, so that both sides have a high sense of presence. Can be felt.

It is a block diagram which shows the structure of the voice processing apparatus which concerns on 1st Embodiment. It is explanatory drawing which shows an example of the command list part which concerns on 1st Embodiment. It is a block diagram which shows the structure of the voice processing apparatus which concerns on 2nd Embodiment. It is a block diagram which shows the structure of the voice processing apparatus which concerns on 3rd Embodiment. It is a block diagram which shows the structure which adapted the audio processing apparatus which concerns on a modification embodiment to a video conferencing system.

(A) First Embodiment In the following, an embodiment of the voice processing device, the voice processing program, and the voice processing method of the present invention will be described in detail with reference to the drawings.

The first embodiment illustrates, for example, a case where the above-described voice processing device, voice processing program, and voice processing method of the present invention are applied to a microphone input unit of a video conferencing system, a telephone conferencing system, or the like.

(A-1) Configuration of First Embodiment FIG. 1 is a block diagram showing a configuration of a voice processing device 100 according to the first embodiment.

The voice processing device 100 of the first embodiment of the present invention may be constructed as a dedicated board, for example, or is realized by writing a voice processing program to a DSP (digital signal processor). It may be realized by a CPU and software (speech processing program) executed by the CPU, but functionally, it can be represented by FIG.

In FIG. 1, the voice processing device 100 according to the first embodiment of the present invention includes a microphone 101, a microphone amplifier 102, an AD converter 103, and a call processing unit 104.

The microphone 101 is a microphone that receives human voice or sound.

The microphone amplifier 102 amplifies the input signal received by the microphone 101.

The AD converter 103 converts the signal amplified by the microphone amplifier 102 from an analog signal to a digital signal. Hereinafter, the signal converted by the AD converter 103 will be referred to as a “microphone input signal”.

The call processing unit 104 outputs the input microphone input signal to the output terminal, and at the same time saves the microphone input signal in the audio buffer. Further, the call processing unit 104 recognizes the microphone input signal by voice, and when the voice recognition result matches one of the commands in the command list unit, switches to output the sound signal stored in the audio buffer for a certain period of time. , When the output is completed for a certain period of time, the microphone input signal is output again.

Next, the detailed configuration of the call processing unit 104 will be described.

The call processing unit 104 includes an input terminal 105, an audio buffer unit 106, a voice recognition unit 107, a command list unit 108, a command determination unit 109, an output switching unit 110, and an output terminal 111.

The input terminal 105 is an interface for calling a microphone input signal and inputting it to the processing unit 104.

The audio buffer unit 106 is a buffer that holds the microphone input signal for a certain period of time.

The voice recognition unit 107 recognizes the microphone input signal by voice and outputs the result of the voice recognition.

The command list unit 108 is a list in which commands are held. The command list unit 108 holds a list of commands in a text file as shown in FIG. 2, for example. Note that FIG. 2 is an example, and various values (formats) can be applied to the content and format of the data to be retained.

The command determination unit 109 determines whether or not the voice recognition result exists in the command list of the command list unit 108, and outputs the determination result.

The output switching unit 110 determines the sound signal to be output from the command determination result, and outputs the sound signal.

The output terminal 111 is an interface that outputs the sound signal of the call processing unit 104.

(A-2) Operation of First Embodiment The operation of the voice processing device 100 according to the first embodiment of the present invention will be described in detail.

First, when the operation of the voice processing device 100 starts, a sound signal such as a voice emitted by a speaker or an analog sound signal on which an environmental sound is superimposed is input to the microphone 101.

The input signal input to the microphone 101 is amplified by the microphone amplifier 102, converted from an analog signal to a digital signal by the AD converter 103, and input as a microphone input signal x (n) to the input terminal 105 of the call processing unit 104. NS.

When a signal starts to be input to the input terminal 105 of the call processing unit 104, the call processing unit 104 first outputs the microphone input signal x (n) to the output switching unit 110.

When the voice processing device 100 is operating, the output switching unit 110 outputs a silent signal as an output signal y (n) to the output terminal 111 as shown in the following equation (1).
y (n) = 0 ... (1)

At the same time, the call processing unit 104 holds the microphone input signal x (n) at the write position write_index of the audio buffer buffer (n) of the audio buffer unit 106 according to the following equation (2). After holding, the call processing unit 104 advances (increments) the writing position write_index as shown in the following equation (3).

BUFFER_SIZE in the above equation (3) is the buffer length of the audio buffer of the audio buffer unit 106.

Further, the call processing unit 104 simultaneously performs voice recognition of the microphone input signal x (n) by the voice recognition unit 107, and outputs the voice recognition result to the command determination unit 109.

The command determination unit 109 compares the voice recognition result with the command list held in the command list unit 108, determines whether or not the voice recognition result exists in the command list, and outputs the determination result. Output to unit 110.

When the command determination unit 109 determines that the voice recognition result of the voice recognition unit 107 does not exist in the command list of the command list unit 108, the output switching unit 110 continues to output a silent signal to the output terminal 111.

On the other hand, when the command determination unit 109 determines that the voice recognition result of the voice recognition unit 107 exists in the command list of the command list unit 108, the output switching unit 110 sets the read position read_index of the audio buffer unit 106. Calculate according to the following formula (4).

The LEN of the above equation (4) is a length for reproducing the microphone input signal held in the audio buffer unit 106. As a method for determining LEN, various methods can be widely applied, and there is a method of making a constant such that the length is the same as the buffer size of the audio buffer unit 106 (LEN = BUFFER_SIZE). Alternatively, a method may be used in which the microphone input signal held in the audio buffer unit 106 is subjected to voice section processing, the length of the calling voice is obtained, and the length is set to LEN.

Then, as shown in the following equation (5), the output switching unit 110 uses the sound signal held in the audio buffer unit 106 as the output signal y (n) at the output terminal 111 for a certain period of time (for example, the time length of LEN). Minutes) Output and advance (increment) the read position read_index as shown in Eq. (6) below.

When the output switching unit 110 outputs the sound signal held in the audio buffer unit 106 for a certain period of time, the output switching unit 110 outputs the microphone input signal x (n) as the output signal y (n) as shown in the following equation (7). Output to terminal 111.
y (n) = x (n) ... (7)

(A-3) Effect of First Embodiment As described above, according to the first embodiment, the voice processing device 100 holds the microphone input signal in the audio buffer, simultaneously performs voice recognition, and performs microphone input. When the signal is determined to be the calling voice, the calling voice held in the audio buffer is output. As a result, the voice processing device 100 can transmit the call voice to the other party, so that a state close to a face-to-face conversation can be reproduced, and the conversation can be started with a high sense of presence.

(B) Second Embodiment Next, a second embodiment of the voice processing device, the voice processing program, and the voice processing method of the present invention will be described in detail with reference to the drawings.

The second embodiment illustrates a case where the sound output method of the voice processing device of the present invention is different from that of the first embodiment.

(B-1) Configuration of Second Embodiment FIG. 3 is a block diagram showing a configuration of a voice processing device 200 according to the second embodiment.

The voice processing device 200 of the second embodiment is different from the voice processing device 100 of the first embodiment in that the signal addition unit 202 is used as a component instead of the output switching unit 110. The other components are the same as or correspond to the components of the voice processing device 100 of FIG. 1 according to the first embodiment. In FIG. 3, the same or corresponding components of the voice processing device 100 according to the first embodiment are designated by the same reference numerals.

Further, since the detailed description of the components that are the same as or correspond to those of the first embodiment is duplicated, they will be omitted here.

In FIG. 3, the voice processing device 200 according to the second embodiment of the present invention includes a microphone 101, a microphone amplifier 102, an AD converter 103, and a call processing unit 201.

Further, the call processing unit 201 has an input terminal 105, an audio buffer unit 106, a voice recognition unit 107, a command list unit 108, a command determination unit 109, a signal addition unit 202, and an output terminal 111.

The signal addition unit 202 determines from the command determination result whether to output the sound signal of either the microphone input signal or the signal obtained by adding the microphone input signal and the audio buffer unit, and outputs the determined sound signal.

(B-2) Operation of the Second Embodiment The basic operation of the voice processing in the voice processing device 200 according to the second embodiment is the same as the voice processing described in the first embodiment.

Hereinafter, the processing operation in the signal addition unit 202, which is different from the first embodiment, will be described in detail.

When the command determination unit 109 determines that the voice recognition result of the voice recognition unit 107 does not exist in the command list of the command list unit 108, the signal addition unit 202 outputs the microphone input signal x (n) to the output terminal 111. Output to. On the other hand, when the command determination unit 109 determines that the result of the voice recognition of the voice recognition unit 107 exists in the command list of the command list unit 108, the signal addition unit 202 sets the audio buffer according to the above equation (4). The read position read_index of unit 106 is calculated.

Then, the signal addition unit 202 adds the sound signal held in the audio buffer unit 106 and the microphone input signal according to the following equation (8), and the added signal is used as the output signal y (n) at the output terminal 111. The output is performed for a certain period of time, and the read position read_index is advanced (incremented) according to the above equation (6).
y (n) = x (n) + buffer (read_index)… (8)

When the signal addition unit 202 outputs the added signal for a certain period of time, the signal addition unit 202 outputs the microphone input signal x (n) as the output signal y (n) to the output terminal 111 according to the above-mentioned equation (7).

(B-3) Effect of Second Embodiment As described above, according to the second embodiment, the voice processing device 200 audios the microphone input signal when the voice recognition result exists in the command list. Outputs a signal obtained by adding the signals held in the buffer. As a result, the voice processing device 200 can output the calling voice without interrupting the sound signal with less delay in sound.

(C) Third Embodiment Next, a third embodiment of the voice processing device, the voice processing program, and the voice processing method of the present invention will be described in detail with reference to the drawings.

The third embodiment illustrates a case where the sound output method of the voice processing device of the present invention is different from the first embodiment and the second embodiment.

(C-1) Configuration of Third Embodiment FIG. 4 is a block diagram showing a configuration of a voice processing device according to the third embodiment.

The voice processing device 300 of the third embodiment has a delay recovery unit 303 as a component in addition to the voice processing device 100 configuration of the first embodiment, and an output switching unit 302 instead of the output switching unit 110. Is different from the voice processing device 100 of the first embodiment and the voice processing device 200 of the second embodiment in that In FIG. 4, the same reference numerals are given to the components that are the same as or correspond to the components of the voice processing device 100 according to the first embodiment.

Further, since the detailed description of the components that are the same as or correspond to those of the first embodiment is duplicated, they will be omitted here.

In FIG. 4, the voice processing device 300 according to the third embodiment of the present invention includes a microphone 101, a microphone amplifier 102, an AD converter 103, and a call processing unit 301.

Further, the call processing unit 301 has an input terminal 105, a delay recovery unit 303, an audio buffer unit 106, a voice recognition unit 107, a command list unit 108, a command determination unit 109, an output switching unit 302, and an output terminal 111.

The output switching unit 302 determines the sound signal to be output from the command determination result, and outputs the sound signal. Further, it is output to the delay recovery unit 303 whether or not the output sound signal has been switched.

The delay recovery unit 303 adjusts the output timing of the microphone input signal from the input terminal 105 to the output switching unit 110. For example, the delay recovery unit 303 delays the input microphone input signal by a predetermined time and outputs the microphone input signal.

(C-3) Operation of the Third Embodiment The basic operation of the voice processing in the voice processing device 300 according to the third embodiment is the same as the call processing described in the first embodiment.

Hereinafter, the processing operations in the output switching unit 302 and the delay recovery unit 303, which are different from the first embodiment, will be described in detail.

When a signal starts to be input to the input terminal 105 of the call processing unit 301, the call processing unit 301 outputs the microphone input signal x (n) to the delay recovery unit 303.

The delay recovery unit 303 outputs the microphone input signal x (n) to the output switching unit 302 when the operation of the voice processing device 300 starts.

When the voice processing device 100 is operating, the output switching unit 302 outputs a silent signal as an output signal y (n) to the output terminal 111 as shown in the above equation (1).

When the command determination unit 109 determines that the voice recognition result of the voice recognition unit 107 does not exist in the command list of the command list unit 108, the output switching unit 302 continues to output a silent signal to the output terminal 111.

On the other hand, when the command determination unit 109 determines that the voice recognition result of the voice recognition unit 107 exists in the command list of the command list unit 108, the output switching unit 302 sets the read position read_index of the audio buffer unit 106. Calculate according to the above equation (4).

Then, the output switching unit 302 outputs the sound signal held in the audio buffer unit 106 as the output signal y (n) to the output terminal 111 for a certain period of time as shown in the above-mentioned equation (5), and outputs the sound signal to the output terminal 111 for a certain period of time. ) The read position read_index is advanced (incremented) as shown in the equation.

When the output switching unit 302 outputs the sound signal held in the audio buffer unit 106 for a certain period of time, the output is completed, and the output switching unit 302 outputs a signal informing that the output sound signal has been switched to the delay recovery unit 303.

When the sound signal output from the output switching unit 302 is switched, the delay recovery unit 303 performs a delay recovery process for a predetermined time on the microphone input signal x (n) and outputs the microphone input signal x (n) to the output switching unit 110. The delay recovery time may be determined in consideration of the processing times of the voice recognition unit 107 and the command determination unit 109, or may be the same as the length of the call voice output from the audio buffer unit. Further, the delay recovery process of the delay recovery unit 303 outputs the microphone input signal x'(n) obtained by converting the speech speed of the microphone input signal x (n), and inputs the microphone when the delay corresponding to the delay recovery time is recovered. The signal x (n) may be output, or the microphone input signal x'' (n) that detects the audio section and deletes the silence for the delay recovery time is output to the microphone input signal x (n). When the delay corresponding to the delay recovery time is recovered, the microphone input signal x (n) may be output. Further, the processing of the delay recovery unit 303 may be performed after the processing of the output switching unit 110.

When the delay recovery process is completed, the output switching unit 302 outputs the microphone input signal x (n) as the output signal y (n) to the output terminal 111 as shown in the above equation (7).

(C-3) Effect of Third Embodiment As described above, according to the third embodiment, the voice processing device 300 is provided with the delay recovery unit 303, so that the call output from the audio buffer unit 106 is made. It is possible to recover the delay of the voice signal for the time. As a result, as compared with the first embodiment, the calling voice can be output without further interruption of the sound signal.

(D) Other Embodiments Although various modified embodiments have been described in each of the above-described embodiments, the present invention can also be applied to the following modified embodiments.

(D-1) The voice processing device described in each of the above-described embodiments starts a call by a command by inputting voice when starting a call in a video call or a conference call as shown in FIG. 5, for example. It may be mounted on the device to be used. In FIG. 5, the connection determination unit 402 determines the connection with the network 405 (for example, the videophone of the other party) based on the voice recognition result by the voice recognition unit 107 and the command determination result based on the command determination unit 109. The connection determination result is output to the NW communication unit 404 via the output terminal 403. The NW communication unit 404 performs connection processing with the network 405 based on the connection determination result. After the connection, the voice processing device exchanges voice with the network 405 via the NW communication unit 404. The sound from the network 405 is converted from a digital signal to an analog signal by the DA converter 406 via the NW communication unit 404, amplified by the speaker amplifier 407, and output by the speaker 408.

100 ... voice processing device, 101 ... microphone, 102 ... microphone amplifier, 103 ... AD converter, 104 ... call processing unit, 105 ... input terminal, 106 ... audio buffer unit, 107 ... voice recognition unit, 108 ... command list unit, 109 ... Command determination unit, 110 ... Output switching unit, 111 ... Output terminal, 200 ... Voice processing unit, 201 ... Call processing unit, 202 ... Signal addition unit, 300 ... Voice processing device, 301 ... Call processing unit, 302 ... Output Switching unit, 303 ... Delay recovery unit, 402 ... Connection determination unit, 403 ... Output terminal, 404 ... NW communication unit, 405 ... Network, 406 ... DA converter, 407 ... Speaker amplifier, 408 ... Speaker.

Claims (5)

A buffer for playing back the connection command voice transmitted after connecting to the other side, and a buffer unit that holds the input signal including the above connection command voice for a certain period of time.
A voice recognition unit that performs voice recognition for the above input signal,
Using the results of the speech recognition unit, the input signal, and the connection command voice determining whether the command judging section,
When the command determination unit determines that the input signal is the connection command voice, the input signal held in the buffer unit is output, and the voice held in the buffer unit is output. A voice processing device characterized by having an output switching unit that switches to output an input signal. When the command determination unit determines that the input signal is the connection command voice, the output switching unit adds the current input signal to the input signal held in the buffer unit and outputs the output. The voice processing apparatus according to claim 1, wherein the voice processing apparatus is used. The voice processing apparatus according to claim 1, further comprising a delay recovery unit for adjusting the timing of inputting the input signal to the output switching unit. Computer,
A buffer for playing back the connection command voice transmitted after connecting to the other side, and a buffer unit that holds the input signal including the above connection command voice for a certain period of time.
A voice recognition unit that performs voice recognition for the above input signal,
Using the results of the speech recognition unit, the input signal, and the connection command voice determining whether the command judging section,
When the command determination unit determines that the input signal is the connection command voice, the input signal held in the buffer unit is output, and the voice held in the buffer unit is output. A voice processing program characterized by functioning as an output switching unit that switches to output an input signal. It has a buffer unit, a voice recognition unit, a command determination unit, and an output switching unit.
The buffer unit is used to reproduce the connection command voice transmitted after connecting to the other side on the other side, and holds the input signal including the connection command voice for a certain period of time.
The voice recognition unit performs voice recognition on the input signal and performs voice recognition.
The command determination unit uses the result of the speech recognition unit, the input signal is judged whether the connection command voice,
When the command determination unit determines that the input signal is the connection command voice, the output switching unit outputs the input signal held in the buffer unit and holds the input signal in the buffer unit. A voice processing method characterized by switching to output the above input signal after outputting voice.

Images