JP6995907B2 - Speech processing equipment, audio processing methods and programs - Google Patents

Description

Embodiments of the present invention relate to speech processing devices, speech processing methods and programs.

Communicating the right message in the everyday environment is very important. In particular, it is necessary to reliably deliver alerts and danger notifications in car navigation, as well as messages that should be notified without being buried in the surrounding environmental sounds in emergency disaster broadcasting, even when considering subsequent actions.

Widely used methods for alerting and notifying danger in car navigation include stimulation by light and addition of a buzzer sound.

Japanese Unexamined Patent Publication No. 2007-019980

However, in the prior art, since the attention is alerted by increasing the stimulus from the normal voice guide, a phenomenon that the user such as the driver is surprised at the moment of the alert is caused. After being surprised, the user's behavior tends to be delayed, and although the stimulus should originally promote smooth crisis avoidance behavior, it may result in restricting the behavior.

The voice processing device of the embodiment includes a specific unit and a modulation unit. The specific unit specifies any one or more of the one or more voices included in the voice to be output as the emphasized portion based on the attributes of the voice. The modulation unit is the first sound so that at least one of the pitch and the phase is different between the emphasized part of the first sound output to the first output part and the emphasized part of the second sound output to the second output part. And at least one of the emphasized parts of the second voice is modulated.

The block diagram of the voice processing apparatus which concerns on 1st Embodiment. The figure which shows an example of the arrangement of the speaker of an embodiment. The figure which shows an example of the measurement result. The figure which shows the other example of the arrangement of the speaker of an embodiment. The figure which shows the other example of the arrangement of the speaker of an embodiment. The figure for demonstrating pitch modulation and phase modulation. The figure which shows the relationship between the phase difference (degree) and the sound pressure (dB) of a background sound. The figure which shows the relationship between the frequency difference (Hz) and the sound pressure (dB) of a background sound. The flowchart of audio output processing in 1st Embodiment. The block diagram of the voice processing apparatus which concerns on 2nd Embodiment. The flowchart of audio output processing in 2nd Embodiment. The block diagram of the voice processing apparatus which concerns on 3rd Embodiment. The flowchart of audio output processing in 3rd Embodiment. The block diagram of the voice processing apparatus which concerns on 4th Embodiment. The figure which shows an example of the structure of the data stored in a storage part. The flowchart of audio output processing in 4th Embodiment. The figure which shows an example of the specification screen for specifying the part to be learned. The figure which shows an example of the learning screen. The figure which shows the other example of the learning screen. The figure which shows the other example of the learning screen. The figure which shows the other example of the learning screen. The hardware block diagram of the voice processing apparatus which concerns on embodiment.

Hereinafter, preferred embodiments of the voice processing apparatus according to the present invention will be described in detail with reference to the accompanying drawings.

In the inventor's experiment, when listening to audio with different pitch and phase from each of multiple audio output devices (speakers, headphones, etc.), it is perceived regardless of the physical loudness of the audio. It has been confirmed that the clarity is increased and the attention level is increased. At this time, almost no sense of surprise is observed.

The conventional way of thinking is that when listening to audio having a different pitch or phase from each of a plurality of audio output devices, the clarity is reduced and the hearing is deteriorated. However, as described above, in the inventor's experiment, it was confirmed that the clarity is increased and the attention level is increased when listening to sounds having different pitches and phases with the left and right ears.

This is a new discovery that has never been seen before, as hearing works by using both ears to perceive speech more clearly. The following embodiments are based on this finding and allow alerting and danger notification to the left and right ears by utilizing voice perception with different pitch and phase.

(First Embodiment)
The voice processing apparatus according to the first embodiment modulates at least one of the pitch and the phase of the voice corresponding to the emphasized portion, and outputs the modulated voice. This makes it possible to increase the user's attention and smoothly execute the next operation without changing the strength of the audio signal.

FIG. 1 is a block diagram showing an example of the configuration of the voice processing device 100 according to the first embodiment. As shown in FIG. 1, the voice processing device 100 includes a storage unit 121, a reception unit 101, a specific unit 102, a modulation unit 103, an output control unit 104, and speakers 105-1 to 105-n (n is). An integer of 2 or more) and.

The storage unit 121 stores various data used in the voice processing device 100. For example, the storage unit 121 stores the input text data, data indicating an emphasized portion specified from the text data, and the like. The storage unit 121 can be configured by any commonly used storage medium such as an HDD (Hard Disk Drive), SSD (Solid State Drive), optical disk, memory card, and RAM (Random Access Memory).

The speakers 105-1 to 105-n are output units that output voice according to instructions from the output control unit 104. Since the speakers 105-1 to 105-n have the same configuration, they may be simply referred to as the speaker 105 when it is not necessary to distinguish them. In the following, at least one of the pitch and the phase is modulated between the sounds output to the set of two speakers, the speaker 105-1 (first output unit) and the speaker 105-2 (second output unit), as an example. explain. Similar processing may be applied to two or more sets.

The reception unit 101 receives various data to be processed. For example, the reception unit 101 receives an input of text data to be converted into voice and output.

The specific unit 102 specifies an emphasized portion representing a portion to be emphasized and output in the sound to be output. The emphasized portion corresponds to a portion where at least one of the pitch and the phase is modulated and output in order to call attention and give a danger notification. For example, the specific unit 102 identifies the emphasized portion from the input text data. When the information for specifying the emphasized portion is added to the input text data in advance, the specifying unit 102 can specify the emphasized portion by referring to the added information (additional information). The specifying unit 102 may specify the emphasized portion by collating the text data with the data indicating the predetermined emphasized portion. The identification unit 102 may execute both the identification by the additional information and the identification by the data collation. The data indicating the emphasized portion may be stored in the storage unit 121 or may be stored in a storage device external to the voice processing device 100.

The specific unit 102 may execute a coding process for adding information (additional information) indicating that the specified emphasized portion is emphasized to the text data. The modulation unit 103 in the subsequent stage can determine the emphasized portion to be modulated by referring to the additional information added in this way. The additional information may be in any format as long as it can be determined that it is an emphasized portion. Further, the specific unit 102 may store the text data subjected to the coding process in a storage medium such as the storage unit 121. As a result, in the subsequent voice output processing, it becomes possible to use the text data to which additional information is added in advance.

The modulation unit 103 modulates a modulation target that is at least one of the pitch and the phase of the sound to be output. For example, in the modulation unit 103, the modulation target is different between the emphasized portion of the voice (first voice) output to the speaker 105-1 and the emphasized portion of the voice (second voice) output to the speaker 105-2. , Modulates the modulation target of at least one of the emphasized parts of the voice.

In the present embodiment, the modulation unit 103 sequentially determines whether the text data is the emphasized portion when generating the voice obtained by converting the text data, and executes the modulation process on the emphasized portion. That is, when the modulation unit 103 converts the text data to generate a voice (first voice) to be output to the speaker 105-1 and a voice (second voice) to be output to the speaker 105-2, the text of the emphasized portion is generated. For the data, the first voice and the second voice in which at least one modulation target is modulated are generated so that the modulation targets are different from each other.

For the process of converting text data into speech (speech synthesis process), any conventionally used method such as formant speech synthesis and speech corpus-based speech synthesis can be used.

When the phase is modulated, the modulation unit 103 may invert the polarity of the signal input to one of the speaker 105-1 and the speaker 105-2. As a result, one of the speakers 105 is out of phase with respect to the other, and the same function as in the case of modulating the phase of the voice data can be realized.

The modulation unit 103 may confirm the completeness of the data to be processed, and may perform the modulation processing when the completeness is confirmed. For example, when the additional information added to the text data is in a format in which information indicating the start of the emphasized portion and information indicating the end of the emphasized portion are specified, the modulation unit 103 includes information indicating the start and information indicating the end. If it is confirmed that the above corresponds to, the modulation processing may be performed.

The output control unit 104 controls the output of audio from the speaker 105. For example, the output control unit 104 outputs the first voice to which the modulation target is modulated to the speaker 105-1 and outputs the second voice from the speaker 105-2. When a speaker 105 other than the speaker 105-1 and the speaker 105-2 is provided, the output control unit 104 assigns the optimum voice to each speaker 105 and outputs the speaker 105. Each speaker 105 outputs sound based on the output data from the output control unit 104.

The output control unit 104 calculates the output (amplifier output) to each speaker 105 by using parameters such as the position and characteristics of the speaker 105. These parameters are stored, for example, in the storage unit 121.

For example, when the required sound pressures of the two speakers 105 are made uniform, the amplifier outputs W1 and W2 to each speaker are calculated as follows. Let the distance between the two speakers be L1 and L2. L1 (L2) is, for example, the distance between the speaker 105-1 (speaker 105-2) and the center of the head. The distance from each speaker 105 to the nearest ear may be used. The gain of the speaker 105-1 (speaker 105-2) in the audible region of the voice to be used is Gs1 (Gs2). It is assumed that when the distance is doubled, the sound pressure drops by 6 dB, and the amplifier output needs to be doubled to raise the sound pressure by 3 dB. In order to make the sound pressures in both ears uniform, the output control unit 104 calculates and determines the amplifier outputs W1 and W2 so that the following equation holds.
-6 x (L1 / L2) x (1/2) + (2/3) x Gs1 x W1 =
-6 x (L2 / L1) x (1/2) + (2/3) x Gs2 x W2

The reception unit 101, the specific unit 102, the modulation unit 103, and the output control unit 104 may be realized by, for example, having one or more processors such as a CPU (Central Processing Unit) execute a program, that is, by software. However, it may be realized by one or more processors such as an IC (Integrated Circuit), that is, hardware, or may be realized by using software and hardware in combination.

FIG. 2 is a diagram showing an example of the arrangement of the speaker 105 of the present embodiment. FIG. 2 shows an example of the arrangement of the speaker 105 when the user 205 is observed from vertically above to below. From the speaker 105-1 and the speaker 105-2, the sound that has been modulated by the modulation unit 103 flows. The speaker 105-1 is placed on the extension of the right ear of the user 205. The speaker 105-2 can be placed at an angle with respect to a line passing through the speaker 105-1 and the right ear.

The inventor changed the position of the speaker 105-2 along the curve 203 or the curve 204, measured the attention when the pitch- and phase-modulated sound was output, and confirmed the increase in the attention in either case. did. Attention was measured using evaluation criteria such as EEG (Electroencephalogram), NIRS (Near-Infrared Spectroscopy), and subjective evaluation.

FIG. 3 is a diagram showing an example of measurement results. The horizontal axis of the graph in FIG. 3 represents the arrangement angle of the speaker 105. The arrangement angle is, for example, an angle formed by a line connecting the speaker 105-1 and the user 205 and a line connecting the speaker 105-2 and the user 205. As shown in FIG. 3, the increase in attention is large when the arrangement angle is from 90 ° to 180 °. Therefore, it is desirable that the speaker 105-1 and the speaker 105-2 are arranged so that the arrangement angle is from 90 ° to 180 °. Since attention is detected, if the arrangement angle is larger than 0 °, it may be smaller than 90 °.

The pitch or phase of the entire section of the voice may be modulated, but in this case, attention may be reduced due to habituation or the like. Therefore, the modulation unit 103 modulates only the emphasized portion specified by the additional information or the like. This makes it possible to more effectively increase attention to the emphasized portion.

FIG. 4 is a diagram showing another example of the arrangement of the speaker 105 of the present embodiment. FIG. 4 shows an example of an arrangement of a speaker 105 installed for outputting an out-of-field broadcast, for example, outdoors. As shown in FIG. 3, it is desirable to use a set of speakers 105 having an arrangement angle of 90 ° to 180 °. Therefore, in the example of FIG. 4, the voice modulation process is executed for the set of the speaker 105-1 and the speaker 105-2 arranged at the arrangement angle of 180 °.

FIG. 5 is a diagram showing another example of the arrangement of the speaker 105 of the present embodiment. FIG. 5 shows an example in which the speaker 105-1 and the speaker 105-2 are configured as headphones.

The arrangement example of the speaker 105 is not limited to FIGS. 2, 4 and 5. As shown in FIG. 3, any combination of speakers may be used as long as they are arranged at an arrangement angle that allows attention to be obtained. For example, the present embodiment may be applied to a plurality of speakers used for car navigation.

Next, pitch modulation and phase modulation will be described. FIG. 6 is a diagram for explaining pitch modulation and phase modulation. The phase modulation outputs a signal 603 in which the peak time position is changed without changing the wave number within a unit time for the same envelope with respect to the original signal 601 based on the envelope 604 of the voice. .. Pitch modulation outputs a signal 602 with a changed wave number.

Next, the relationship between pitch or phase modulation and the audibility of speech will be described. FIG. 7 is a diagram showing the relationship between the phase difference (degrees) and the sound pressure (dB) of the background sound. The phase difference represents the phase difference between the sounds output from the two speakers 105 (for example, the difference between the phase of the sound output from the speaker 105-1 and the phase of the sound output from the speaker 105-2). The sound pressure of the background sound represents the maximum value (limit sound pressure) of the sound pressure of the background sound that the user can hear the output sound.

The background sound is a sound other than the sound output from the speaker 105. For example, ambient noise and sounds such as music output other than voice correspond to background sounds. The points indicated by the rectangles in FIG. 7 represent the average value of the obtained values. The range indicated by the lines above and below this point represents the standard deviation of the obtained values.

As shown in FIG. 7, even when a background sound of 0.5 dB or more is present, if the phase difference is 60 ° or more and 180 ° or less, the user listens to the sound output from the speaker 105. Can be done. Therefore, the modulation unit 103 may execute the modulation process so that the phase difference is 60 ° or more and 180 ° or less. The modulation unit 103 may execute the modulation process so that the phase difference is 90 ° or more and 180 ° or less, or 120 ° or more and 180 ° or less, which has a higher limit sound pressure.

FIG. 8 is a diagram showing the relationship between the frequency difference (Hz) and the sound pressure (dB) of the background sound. The frequency difference represents the difference in the frequency of the sound output from the two speakers 105 (for example, the difference between the frequency of the sound output from the speaker 105-1 and the frequency of the sound output from the speaker 105-2). The points indicated by the rectangles in FIG. 8 represent the average value of the obtained values. Of the numerical values "A, B" attached next to this point, A represents the frequency difference and B represents the sound pressure of the background sound.

As shown in FIG. 8, even when the background sound is present, the user can hear the sound output from the speaker 105 if the frequency difference is 100 Hz (hertz) or more. Therefore, the modulation unit 103 may execute the modulation process so that the frequency difference is 100 Hz or more within the audible range.

Next, the voice output processing by the voice processing device 100 according to the first embodiment configured in this way will be described with reference to FIG. FIG. 9 is a flowchart showing an example of audio output processing according to the first embodiment.

The reception unit 101 accepts the input of text data (step S101). The specific unit 102 determines whether or not additional information is added to the text data (step S102). When it is not added (step S102: No), the specific unit 102 specifies the emphasized portion from the text data (step S103). For example, the specific unit 102 identifies the emphasized portion by collating the input text data with the data indicating the predetermined emphasized portion. The specific unit 102 adds additional information indicating the emphasized portion to the emphasized portion of the corresponding text data (step S104). The method of adding the additional information may be any method as long as the modulation unit 103 can specify the emphasized portion.

After the additional information is added (step S104) and when the additional information is added to the text data (step S102: Yes), the modulation unit 103 is a voice corresponding to the text data and is an emphasized portion. For the text data, a voice (first voice, second voice) in which the modulation target is modulated so that the modulation targets are different from each other is generated (step S105).

The output control unit 104 determines the sound to be output for each speaker 105, and outputs the determined sound (step S106). Each speaker 105 outputs sound according to the instruction of the output control unit 104.

As described above, in the voice processing apparatus according to the first embodiment, while generating the voice corresponding to the text data, at least one of the pitch and the phase of the voice is modulated with respect to the text data corresponding to the emphasized portion. , Outputs modulated audio. This makes it possible to increase the user's attention without changing the strength of the audio signal.

(Second embodiment)
In the first embodiment, when the text data is sequentially converted into speech, the text data in the emphasized portion is modulated. The voice processing device according to the second embodiment generates a voice for text data, and then performs a modulation process on the voice corresponding to the emphasized portion of the generated voice.

FIG. 10 is a block diagram showing an example of the configuration of the voice processing device 100-2 according to the second embodiment. As shown in FIG. 10, the voice processing device 100-2 includes a storage unit 121, a reception unit 101, a specific unit 102, a modulation unit 103-2, an output control unit 104, and speakers 105-1 to 105-. n and a generation unit 106-2 are provided.

In the second embodiment, the function of the modulation unit 103-2 and the addition of the generation unit 106-2 are different from the first embodiment. Other configurations and functions are the same as those in FIG. 1, which is a block diagram of the voice processing device 100 according to the first embodiment. Therefore, the same reference numerals are given, and the description thereof is omitted here.

The generation unit 106-2 generates the voice corresponding to the text data. For example, the generation unit 106-2 converts the input text data into a voice output to the speaker 105-1 (first voice) and a voice output to the speaker 105-2 (second voice).

The modulation unit 103-2 performs modulation processing on the voice of the emphasized portion among the voices generated by the generation unit 106-2. For example, the modulation unit 103-2 emphasizes at least one of the first voice and the second voice so that the modulation target differs between the generated first voice enhancement portion and the generated second voice enhancement portion. Modulate the modulation target of the part.

Next, the voice output processing by the voice processing device 100-2 according to the second embodiment configured in this way will be described with reference to FIG. FIG. 11 is a flowchart showing an example of audio output processing according to the second embodiment.

Since steps S201 to S204 are the same processes as steps S101 to S104 in the voice processing device 100 according to the first embodiment, the description thereof will be omitted.

In the present embodiment, when the text data is input, the voice generation process (speech synthesis process) by the generation unit 106-2 is executed. That is, the generation unit 106-2 generates the voice corresponding to the text data (step S205).

After the voice is generated (step S205), after the additional information is added (step S204), and when the additional information is added to the text data (step S202: Yes), the modulation unit 103-2 is generated. The emphasized portion is extracted from the voice (step S206). For example, the modulation unit 103-2 identifies the emphasized portion of the text data by referring to the additional information, and from the correspondence between the text data and the generated voice, the emphasized portion of the voice corresponding to the emphasized portion of the specified text data. To extract. The modulation unit 103-2 executes a modulation process on the emphasized portion of the extracted voice (step S207). Note that the modulation unit 103-2 does not perform modulation processing on the voice other than the emphasized portion.

Since step S208 is the same process as step S106 in the voice processing device 100 according to the first embodiment, the description thereof will be omitted.

As described above, in the voice processing apparatus according to the second embodiment, after generating the voice corresponding to the text data, at least one of the pitch and the phase of the emphasized portion of the voice is modulated, and the modulated voice is output. This makes it possible to increase the user's attention without changing the strength of the audio signal.

(Third embodiment)
In the first and second embodiments, text data is input, and the text data is converted into voice and output. Such an embodiment can be applied, for example, to output a predetermined text data for emergency disaster broadcasting. On the other hand, it is conceivable that the voice uttered by the user is output for emergency disaster broadcasting. The voice processing device according to the third embodiment inputs voice from a voice input device such as a microphone, and performs modulation processing on the emphasized portion of the input voice.

FIG. 12 is a block diagram showing an example of the configuration of the voice processing device 100-3 according to the third embodiment. As shown in FIG. 12, the voice processing device 100-3 includes a storage unit 121, a reception unit 101-3, a specific unit 102-3, a modulation unit 103-3, an output control unit 104, and a speaker 105-. 1 to 105-n and a generation unit 106-2 are provided.

In the third embodiment, the functions of the reception unit 101-3, the specific unit 102-3, and the modulation unit 103-3 are different from those of the second embodiment. Other configurations and functions are the same as those in FIG. 10, which is a block diagram of the voice processing device 100-2 according to the second embodiment, and thus the same reference numerals are given, and the description thereof is omitted here.

The reception unit 101-3 receives not only text data but also voice input from a voice input device such as a microphone. Further, the reception unit 101-3 receives the designation of the portion to be emphasized in the input voice. For example, the reception unit 101-3 accepts the user's pressing of a predetermined button as a designation indicating that the voice input after the pressing is the emphasized portion. The reception unit 101-3 may accept the designation of the start and end of the emphasized portion as a designation indicating that the voice input from the start to the end is the portion to be emphasized. The designation method is not limited to these, and any method may be used as long as it is possible to determine the part to be emphasized in the voice. In the following, the designation of the emphasized part of the voice may be referred to as a trigger.

The specific unit 102-3 further has a function of specifying the emphasized portion of the voice based on the received designation (trigger).

The modulation unit 103-3 performs modulation processing on the voice of the emphasized portion of the voice generated by the generation unit 106-2 or the input voice.

Next, the voice output processing by the voice processing device 100-3 according to the third embodiment configured in this way will be described with reference to FIG. FIG. 13 is a flowchart showing an example of audio output processing according to the third embodiment.

The reception unit 101-3 determines whether or not the voice input is prioritized (step S301). Voice input priority is a designation indicating that voice is input and output instead of text data. For example, when the button for designating the voice input priority is pressed, the reception unit 101-3 determines that the voice input priority is given.

The method for determining whether the voice input is prioritized is not limited to this. For example, it may be determined by referring to the information stored in advance indicating whether the voice input is prioritized. Further, when the text data is not input and only the voice input is performed, it is not necessary to execute the voice input priority designation or determination (step S301). In this case, it is not necessary to execute the additional process (step S306) based on the text data described later.

In the case of voice input priority (step S301: Yes), the reception unit 101-3 accepts voice input (step S302). The specific unit 102-3 determines whether or not the designation (trigger) of the portion to be emphasized in the voice is input (step S303).

When the trigger is not input (step S303: No), the identification unit 102-3 specifies the emphasized portion of the voice (step S304). For example, the specifying unit 102-3 collates the input voice with the voice data registered in advance, and specifies the voice that matches or is similar to the registered voice data as the emphasized part. The specifying unit 102-3 may specify the emphasized portion by collating the text data obtained by recognizing the input voice with the data indicating the predetermined emphasized portion.

When it is determined in step S303 that the trigger is input (step S303: Yes), and after the emphasized portion is specified in step S304, the identification unit 102-3 refers to the input voice data. Additional information indicating the emphasized portion is added (step S305). The method of adding the additional information may be any method as long as it can be determined that the voice is the emphasized portion.

When it is determined in step S301 that the voice input priority is not given (step S301: No), additional processing based on the text is executed (step S306). This process can be realized, for example, by the same process as in steps S201 to S205 of FIG.

The modulation unit 103-3 extracts the emphasized portion from the generated voice (step S307). For example, the modulation unit 103-3 extracts the emphasized portion of the voice by referring to the additional information. When step S306 is executed, the modulation unit 103-3 extracts the emphasized portion by the same processing as in step S206 of FIG.

Since steps S308 to S309 are the same processes as steps S207 to S208 in the voice processing device 100-2 according to the second embodiment, the description thereof will be omitted.

As described above, in the voice processing apparatus according to the third embodiment, the emphasized portion of the input voice is specified by a trigger or the like, at least one of the pitch and the phase of the emphasized portion of the voice is modulated, and the modulated voice is output. do. This makes it possible to increase the user's attention without changing the strength of the audio signal.

(Fourth Embodiment)
In the above embodiment, the emphasized portion is specified by referring to, for example, additional information and a trigger. The method of specifying the emphasized part is not limited to this. The voice processing device of the fourth embodiment specifies one or more partial voices among the voices (partial voices) included in the voices to be output as emphasized parts based on the attributes of the partial voices.

In the following, an example of realizing a voice processing device as an application for learning by voice or an application for outputting text data as voice will be described. The learning by voice includes arbitrary learning using voice, for example, learning of a foreign language by voice and learning to output the contents of a subject by voice. An application that outputs text data as voice includes, for example, a reading application that reads out the contents of a book and outputs it by voice. Applicable applications are not limited to these.

By applying it to an application for learning by voice, for example, it is possible to appropriately emphasize the part to be learned and further increase the learning effect. Further, by applying it to an application that outputs text data as voice, it is possible to draw attention to a specific part of voice, for example. Further, by applying it to a reading application, for example, it becomes possible to further increase the presence of the story.

FIG. 14 is a block diagram showing an example of the configuration of the voice processing device 100-4 according to the fourth embodiment. As shown in FIG. 14, the voice processing device 100-4 includes a storage unit 121-4, a display unit 122-4, a reception unit 101-4, a specific unit 102-4, and a modulation unit 103-4. It includes an output control unit 104-4 and speakers 105-1 to 105-n. Since the speakers 105-1 to 105-n are the same as those in FIG. 1, which is a block diagram of the voice processing device 100 according to the first embodiment, they are designated by the same reference numerals, and the description thereof will be omitted here.

The storage unit 121-4 is different from the storage unit 121 of the first embodiment in that the number of output times is further stored as an example of the attribute of the partial voice included in the voice to be output. FIG. 15 is a diagram showing an example of the structure of data stored in the storage unit 121-4. FIG. 15 shows an example of a data structure of data showing a partial voice to be learned. As shown in FIG. 15, this data includes a voice ID, a word, a time, and the number of outputs.

The voice ID is identification information that identifies the voice to be output. For example, a numerical value, a file name of a file for storing voice, or the like can be used as a voice ID.

A word is an example of a learning target, and other information may be a learning target. For example, a non-word object, such as a sentence or chapter containing multiple words, may be used with or in place of the word. The word stored in the storage unit 121-4 may be a part of the words selected by the user or the like among all the words included in the voice, or may be all the words included in the voice. .. An example of how to select a word will be described later.

Time indicates the position of the partial speech corresponding to the word in the speech. Information other than time may be stored as long as the information can specify the position of the partial voice.

Words and times are obtained, for example, by speech recognition of speech used for learning. The voice processing device 100-4 may acquire data as shown in FIG. 15 generated in advance by another device and store it in the storage unit 121-4. The voice processing device 100-4 may store the data obtained by voice recognition of the input voice in the storage unit 121-4.

The number of outputs indicates the number of times that the partial voice corresponding to the word is output. For example, the cumulative value of the number of times the partial voice is output since the learning is started is stored in the storage unit 121-4 as the number of times of output. The number of outputs is an example of the attribute of the partial voice, and information other than the number of outputs may be used as the attribute of the partial voice. Examples of other attributes will be described later.

Returning to FIG. 14, the display unit 122-4 is a display device that displays data used in various processes. The display unit 122-4 can be configured by, for example, a liquid crystal display.

The reception unit 101-4 is different from the reception unit 101 of the first embodiment in that it further accepts the designation of a word to be learned.

The specific unit 102-4 identifies any one or more of the partial voices included in the voice as the emphasized part based on the attributes of the partial voices. For example, when the number of outputs is used as an attribute, the specific unit 102-4 specifies the partial voice whose output number is equal to or less than the threshold value as the emphasized portion. As a result, for example, words that are interpreted as insufficient learning due to a small number of outputs are preferentially emphasized, and it becomes possible to further enhance the learning effect. The same effect can be obtained when the voice output time (for example, the cumulative output time from the start of learning) is used as an attribute instead of the number of outputs.

The modulation unit 103-4 is different from the modulation unit 103 of the first embodiment in that the degree of modulation (modulation intensity) of the emphasized portion is changed based on the attribute. For example, the modulation unit 103-4 modulates at least one of the first voice and the second voice so that the partial voice having a small number of outputs has a higher modulation intensity. The modulation intensity may be changed linearly or non-linearly depending on the number of outputs. The modulation unit 103-4 may have different modulation intensities of each portion included in the emphasized portion. For example, the modulation intensity may be controlled so as to emphasize only the accent portion of the word. It should be noted that the modulation intensity may not be changed based on the attribute. In this case, the same modulation unit 103 as in the first embodiment may be provided.

The output control unit 104-4 is different from the output control unit 104 of the first embodiment in that it further includes a function of controlling the output (display) of various data to the display unit 122-4.

Next, the voice output processing by the voice processing device 100-4 according to the fourth embodiment configured in this way will be described with reference to FIG. FIG. 16 is a flowchart showing an example of audio output processing according to the fourth embodiment.

The reception unit 101-4 accepts the input of text data (step S401). The specifying unit 102-4 identifies the emphasized part from the text data by referring to the attribute (step S402). For example, when the number of outputs is used as an attribute, the specifying unit 102-4 specifies a word whose output number stored in the storage unit 121-4 is equal to or less than a threshold value as an emphasized portion.

The modulation unit 103-4 generates a voice in which the specified emphasized portion is modulated (step S403). For example, the modulation unit 103-4 is a voice corresponding to the specified emphasized portion (word, etc.), and the modulation target is modulated so that the modulation target is different from each other for the emphasized portion (first voice, Second voice) is generated. At this time, the modulation unit 103-4 may generate the first voice and the second voice so as to have the modulation intensity according to the attribute.

The output control unit 104-4 determines the sound to be output for each speaker 105, and outputs the determined sound (step S404). Each speaker 105 outputs sound according to the instruction of the output control unit 104-4.

Next, an example of realizing the speech processing device 100-4 as an application for language learning will be described. The learning application has, for example, the following functions.
(1) A function to specify a part to be learned, that is, an emphasized part, in the voice to be output.
(2) A function to play audio. It may have functions such as pause, rewind, and fast forward.
(3) A function to check whether or not the emphasized part can be understood.
(4) A function to change attributes according to the learning results.

FIG. 17 is a diagram showing an example of a designation screen for designating a portion to be learned. As shown in FIG. 17, the designated screen 1700 is a screen for displaying text data corresponding to the voice to be output. The designated screen 1700 is displayed on the display unit 122-4 by, for example, the output control unit 104-4. The designated screen 1700 is an example of a screen that realizes the function (1) above.

The user selects a part (word, sentence, etc.) to be learned from the text data displayed on the designated screen 1700 with a mouse, a touch panel, or the like. Word 1701 gives an example of a location thus selected.

When the registration button 1711 is pressed, the selected word is stored in the storage unit 121-4 as a learning target. FIG. 15 shows an example of the data stored in this way. The number of outputs in FIG. 15 is set to, for example, "0" at the time of registration. When the cancel button 1712 is pressed, for example, the selection is canceled and the previous screen is displayed.

The method of designating the learning target is not limited to the method shown in FIG. For example, when registration (pressing a button, etc.) is instructed while the voice is being output, the part (word, etc.) that was output at the instructed timing may be registered as a learning target. Data as shown in FIG. 15 is generated by selecting one or more words to be learned independently of the voice and extracting the selected words from the voice (or text data corresponding to the voice). May be good.

By the time the learning is started, it is sufficient that the part to be learned is specified by the method shown in FIG. 17 and the data as shown in FIG. 15 is generated. An example of a screen used for learning will be described below.

FIG. 18 is a diagram showing an example of a learning screen. As shown in FIG. 18, the learning screen 1800 includes a cursor 1801, an output control button 1802, an OK button 1811, and a cancel button 1812.

The output control button 1802 is used for audio reproduction start, pause, reproduction stop, rewind, fast forward, and the like. The cursor 1801 is information for indicating a portion corresponding to the currently reproduced voice. Although FIG. 18 shows an example of a rectangular cursor 1801, the display mode of the cursor 1801 is not limited to this.

When the OK button 1811 is pressed, the learning process ends. When the OK button 1811 is pressed, the data of the storage unit 121-4 may be updated by adding 1 to the number of outputs of each word reproduced so far. For example, the rewind function increases the number of times a word is output when the word is repeatedly played. For example, when the number of times of output of a repeatedly reproduced word exceeds the threshold value, the specifying unit 102-4 does not specify this word as an emphasized part, and specifies only a word whose number of times of output is less than or equal to the threshold value as an emphasized part. This makes it possible to appropriately identify the word to be learned and enhance the learning effect.

When the cancel button 1812 is pressed, for example, the previous screen is displayed. When the cancel button 1812 is pressed, the number of outputs may not be updated.

FIG. 19 is a diagram showing another example of the learning screen. The learning screen 1900 of FIG. 19 is an example of a screen in which a learning result can be specified for each word. The cursor 1901 is displayed for the word corresponding to the voice being played, and the designated window 1910 corresponding to the cursor 1901 is displayed. As the audio reproduction progresses, the cursor 1901 moves and the corresponding designated window 1910 also moves.

The designated window 1910 includes an OK button and a cancel button. For example, when the OK button is pressed, the data in the storage unit 121-4 is updated by adding 1 to the number of outputs of the corresponding word. When the cancel button is pressed, the number of outputs is not updated. If the designated window 1910 includes only the OK button and the OK button is not pressed, the output count may not be updated.

FIG. 20 is a diagram showing another example of the learning screen. In the learning screen 2000 of FIG. 20, the object to be learned (words and the like) is hidden, and the selection window 2010 for selecting the correct answer is displayed. In the selection window 2010, the correct notation of the corresponding word and other notations are displayed selectably. For example, when the correct notation is selected, the data in the storage unit 121-4 is updated by adding 1 to the number of outputs of the corresponding word. If the correct notation is not selected, the output count will not be updated. In such a configuration, the number of correct answers may be stored as an attribute instead of the number of outputs.

FIG. 21 is a diagram showing another example of the learning screen. The learning screen 2100 of FIG. 21 is an example of a screen displaying options at the bottom. The notation of the object to be learned (words, etc.) is hidden, and instead, information associated with the lower option is displayed, such as "Q1", "Q2", and "Q3". The user can select a notation from the choices when the audio is playing or when the audio playback is complete.

Next, another example of the attribute will be described.

In schools and the like, in order to proceed with learning according to a predetermined plan, the target of learning may be changed according to the progress of the plan. Therefore, the elapsed time from the start of learning, for example, the start of voice output may be used as an attribute. In this case, the specifying unit 102-4 identifies different emphasized parts according to the elapsed time. For example, the storage unit 121-4 stores the range of elapsed time for each word instead of the number of outputs in FIG. The specifying unit 102-4 identifies a word whose elapsed time from the start of the actual voice output is included in the range of the stored elapsed time as an emphasized portion. Further, the number of times of repeated use of voice or the like, for example, the number of times of playing a file may be added as an attribute.

A learning unit, such as a learning period and a learning unit, may be an attribute. For example, the storage unit 121-4 stores information for identifying a plurality of learning periods (learning period 1, learning period 2, learning period 3, ...) For each word instead of the number of outputs in FIG. The specifying unit 102-4 specifies a word corresponding to a learning period designated by a user or the like, or a learning period determined based on a predetermined plan, date and time, etc., as an emphasized part.

The type of learning target may be an attribute. For example, when applied to history learning, the storage unit 121-4 determines which type of learning target (word, sentence, etc.) indicates the age, keywords, etc., instead of the number of outputs in FIG. Store as an attribute in. The specifying unit 102-4 specifies a word corresponding to a type specified by a user or the like, or a type determined based on a predetermined plan, date and time, etc., as an emphasized part. When applied to language learning or the like, the storage unit 121-4 may store the part of speech of a word as a type (attribute).

The place where the sound is output may be an attribute. For example, when applied to a reading application, different emphasis may be specified depending on where the reading application is executed and at least one of the number of times the audio is output. This makes it possible to output audio so that the user does not get bored even if the content of the same book is the same.

The priority determined for each learning target may be used as an attribute. The priority indicates the degree to which the target (partial voice corresponding to the target) is prioritized. Any method may be used for determining the priority. For example, the user may select a word and specify a priority. A predetermined word importance (or difficulty) in word dictionary data or the like may be used as a priority. The priority does not have to be fixed and may change dynamically.

For example, the specific unit 102-4 specifies a partial voice corresponding to a word having a priority equal to or higher than a threshold value as an emphasized portion. The specific unit 102-4 may specify the partial voice corresponding to the word in the specified value (designated value) or the specified range (designated range) as the emphasized part. The threshold value, the specified value, and the specified range may be fixed values or may be specified by a user or the like.

For example, the storage unit 121-4 stores the priority for each word instead of the number of outputs in FIG. For example, "1" is set as a priority for the words "mission" and "knowledge", and "2" is set as a priority for the word "aspiration". Then, for example, when the threshold value is set to "1", the specific unit 102-4 specifies the partial voice corresponding to the "mission" and the "knowledge" as the emphasized part. If the priority range can be specified, for example, the emphasized part can be changed according to the importance (difficulty) of the word.

The priority may be configured to change according to other information. For example, the priority may be changed according to the elapsed time from the start of the audio output. If the priority of the word to be learned is raised according to the elapsed time and the priority of the word to be excluded is lowered, the learning according to the above plan becomes possible.

Further, for example, the correct answer may be selected on the screens as shown in FIGS. 20 and 21, and if the answer is correct, the priority may be lowered, and if the answer is not correct, the priority may be increased. This makes it possible to appropriately emphasize objects that are not sufficiently learned. The same function can be realized by using the number of correct answers as an attribute.

In the above description, as in the first embodiment, an example of modulating the emphasized portion while generating the voice corresponding to the text data has been described. The modulation method is not limited to this. For example, as in the second embodiment, the modulation processing may be performed on the voice corresponding to the emphasized portion of the generated voice. Further, the modulation method is not limited to the method of modulating at least one of the pitch and the phase, and other modulation methods may be applied.

As described above, in the voice processing apparatus according to the fourth embodiment, the emphasized portion changed according to the attribute is modulated and output. This makes it possible to improve the learning effect when applied to a learning application and to improve the sense of presence when applied to a reading application.

As described above, according to the first to fourth embodiments, by modulating and outputting at least one of the pitch and the phase of the voice, the attention of the user is increased without changing the strength of the voice signal. It is possible to make it.

Next, the hardware configuration of the voice processing device according to the first to fourth embodiments will be described with reference to FIG. 22. FIG. 22 is an explanatory diagram showing a hardware configuration example of the voice processing device according to the first to fourth embodiments.

The voice processing device according to the first to fourth embodiments includes a control device such as a CPU (Central Processing Unit) 51, a storage device such as a ROM (Read Only Memory) 52 and a RAM (Random Access Memory) 53, and a network. It is provided with a communication I / F 54 that connects to and communicates with a communication unit, and a bus 61 that connects each unit.

The voice processing device in the first to fourth embodiments is a computer or an embedded system, and has either a configuration consisting of one device such as a personal computer and a microcomputer, or a system in which a plurality of devices are connected to a network. You may. Further, the computer in the present embodiment includes not only a personal computer but also an arithmetic processing unit and a microcomputer included in an information processing device, and is a general term for devices or devices capable of realizing the functions in the present embodiment by a program. There is.

The program executed by the voice processing apparatus according to the first to fourth embodiments is provided by being incorporated in the ROM 52 or the like in advance.

The program executed by the voice processing apparatus according to the first to fourth embodiments is a file in an installable format or an executable format, and is a CD-ROM (Compact Disk Read Only Memory), a flexible disk (FD), or a CD. -Recorded on a computer-readable recording medium such as R (Compact Disk Recordable), DVD (Digital Versatile Disk), USB flash memory, SD card, EEPROM (Electrically Erasable Programmable Read-Only Memory), and provided as a computer program product. It may be configured to be.

Further, the program executed by the voice processing device according to the first to fourth embodiments is configured to be stored on a computer connected to a network such as the Internet and provided by downloading via the network. May be good. Further, the program executed by the voice processing device according to the first to fourth embodiments may be configured to be provided or distributed via a network such as the Internet.

The program executed by the voice processing device according to the first to fourth embodiments can make the computer function as each part of the above-mentioned voice processing device. This computer can read a program from a computer-readable storage medium onto the main storage device and execute the program by the CPU 51.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and variations thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

100, 100-2, 100-3, 100-4 Speech processing device 101, 101-3, 101-4 Reception section 102, 102-3, 102-4 Specific section 103, 103-2, 103-3, 103- 4 Modulation unit 104, 104-4 Output control unit 105 Speaker 106-2 Generation unit 121, 121-4 Storage unit 122-4 Display unit

Claims (17)

A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation unit that modulates the pitch of the voice and at least one of the emphasized portions of the second voice is provided.
The attributes are the number of times one or more voices included in the voice to be output are output, the time during which one or more voices included in the voice to be output are output, and after the output of the first voice and the second voice is started. Elapsed time, place to output the sound to be output, type of learning target using the sound to be output, and learning using the sound to be output for a period determined based on a predetermined plan and date and time. At least one of the learning periods,
Voice processing device. A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation unit that modulates the pitch of the voice and at least one of the emphasized portions of the second voice is provided.
The specific part identifies the emphasized part from the input text data, and the specific part identifies the emphasized part.
The modulation unit is the first voice and the second voice corresponding to the text data, and the emphasis is made on at least one of the first voice and the second voice so that the difference is 100 hertz or more. Generates the first voice and the second voice in which the pitch of the portion is modulated.
Voice processing device. A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation unit that modulates the pitch of the voice and at least one of the emphasized portions of the second voice,
A generation unit for generating the first voice and the second voice corresponding to the input text data is provided.
The specific part identifies the emphasized part from the text data, and the specific part identifies the emphasized part.
The modulation unit performs the first voice and the above so that the difference between the emphasized portion of the generated first voice and the emphasized portion of the generated second voice is 100 hertz or more. Modulates the pitch of at least one of the emphasized portions of the second voice,
Voice processing device. A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation unit that modulates the pitch of the voice and at least one of the emphasized portions of the second voice is provided.
Further, the modulation unit further comprises the first voice and 180 ° or less so that the difference between the phase of the emphasized portion of the first voice and the phase of the emphasized portion of the second voice is 60 ° or more and 180 ° or less. Modulates the phase of at least one of the emphasized portions of the second voice.
Voice processing device. A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation unit that modulates the pitch of the voice and at least one of the emphasized portions of the second voice is provided.
The modulation unit further modulates the phase of at least one of the first voice and the second voice by inverting the polarity of the signal input to the first output unit or the second output unit. do,
Voice processing device. The modulation unit changes the degree of modulation of the emphasized portion based on the attribute.
The voice processing device according to any one of claims 1 to 5. The attribute is a priority determined for one or more voices included in the voice to be output.
The voice processing device according to any one of claims 2 to 5. A specific step of specifying any one or more of the one or more voices included in the voice to be output as an emphasized portion based on the attribute of the voice, and
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. Includes a modulation step that modulates the pitch of the audio and at least one of the enhanced portions of the second audio.
The attributes are the number of times one or more voices included in the voice to be output are output, the time during which one or more voices included in the voice to be output are output, and after the output of the first voice and the second voice is started. Elapsed time, place to output the sound to be output, type of learning target using the sound to be output, and learning using the sound to be output for a period determined based on a predetermined plan and date and time. At least one of the learning periods,
Voice processing method. A specific step of specifying any one or more of the one or more voices included in the voice to be output as an emphasized portion based on the attribute of the voice, and
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. Includes a modulation step that modulates the pitch of the audio and at least one of the enhanced portions of the second audio.
In the specific step, the emphasized portion is specified from the input text data, and the emphasized portion is specified.
The modulation step is the first voice and the second voice corresponding to the text data, and at least one of the first voice and the second voice is emphasized so that the difference is 100 hertz or more. Generates the first voice and the second voice in which the pitch of the portion is modulated.
Voice processing method. A specific step of specifying any one or more of the one or more voices included in the voice to be output as an emphasized portion based on the attribute of the voice, and
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation step that modulates the pitch of the audio and at least one of the enhanced portions of the second audio.
A generation step of generating the first voice and the second voice corresponding to the input text data is included.
In the specific step, the emphasized portion is specified from the text data, and the emphasized portion is specified.
The modulation step is such that the difference between the enhanced portion of the generated first voice and the enhanced portion of the generated second voice is 100 hertz or more, the first voice and the said. Modulates the pitch of at least one of the emphasized portions of the second voice,
Voice processing method. A specific step of specifying any one or more of the one or more voices included in the voice to be output as an emphasized portion based on the attribute of the voice, and
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. Includes a modulation step that modulates the pitch of the audio and at least one of the enhanced portions of the second audio.
In the modulation step, the first voice and the first voice and 180 ° or less so that the difference between the phase of the emphasized portion of the first voice and the phase of the emphasized portion of the second voice is 60 ° or more and 180 ° or less. Modulates the phase of at least one of the emphasized portions of the second voice.
Voice processing method. A specific step of specifying any one or more of the one or more voices included in the voice to be output as an emphasized portion based on the attribute of the voice, and
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. Includes a modulation step that modulates the pitch of the audio and at least one of the enhanced portions of the second audio.
The modulation step further modulates the phase of at least one of the first voice and the second voice by inverting the polarity of the signal input to the first output unit or the second output unit. do,
Voice processing method. Computer,
A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. It functions as a modulator that modulates the pitch of the voice and at least one of the emphasized portions of the second voice.
The attributes are the number of times one or more voices included in the voice to be output are output, the time during which one or more voices included in the voice to be output are output, and after the output of the first voice and the second voice is started. Elapsed time, place to output the sound to be output, type of learning target using the sound to be output, and learning using the sound to be output for a period determined based on a predetermined plan and date and time. At least one of the learning periods,
program. Computer,
A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. It functions as a modulator that modulates the pitch of the voice and at least one of the emphasized portions of the second voice.
The specific part identifies the emphasized part from the input text data, and the specific part identifies the emphasized part.
The modulation unit is the first voice and the second voice corresponding to the text data, and the emphasis is made on at least one of the first voice and the second voice so that the difference is 100 hertz or more. Generates the first voice and the second voice in which the pitch of the portion is modulated.
program. Computer,
A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. A modulation unit that modulates the pitch of the voice and at least one of the emphasized portions of the second voice,
It functions as a generation unit that generates the first voice and the second voice corresponding to the input text data.
The specific part identifies the emphasized part from the text data, and the specific part identifies the emphasized part.
The modulation unit performs the first voice and the above so that the difference between the emphasized portion of the generated first voice and the emphasized portion of the generated second voice is 100 hertz or more. Modulates the pitch of at least one of the emphasized portions of the second voice,
program. Computer,
A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. It functions as a modulator that modulates the pitch of the voice and at least one of the emphasized portions of the second voice.
Further, the modulation unit further comprises the first voice and 180 ° or less so that the difference between the phase of the emphasized portion of the first voice and the phase of the emphasized portion of the second voice is 60 ° or more and 180 ° or less. Modulates the phase of at least one of the emphasized portions of the second voice.
program. Computer,
A specific part that specifies any one or more of the one or more voices included in the voice to be output as an emphasized part based on the attribute of the voice, and a specific part.
The first is such that the difference between the frequency of the emphasized portion of the first sound output to the first output unit and the frequency of the emphasized portion of the second sound output to the second output unit is 100 hertz or more. It functions as a modulator that modulates the pitch of the voice and at least one of the emphasized portions of the second voice.
The modulation unit further modulates the phase of at least one of the first voice and the second voice by inverting the polarity of the signal input to the first output unit or the second output unit. do,
program.

Images