JP2016156989A - Voice synthesizer and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique for easy voice synthesis of utterance contents in which a plurality of languages of words are mixed.SOLUTION: A voice synthesizer (karaoke device) acquires utterance content information (S120), and collates a constitution morpheme which is a morpheme constituting the utterance content information with first dictionary data to specify a phonetic sign of the constitution morpheme (S160). The first dictionary data is obtained by associating each morpheme with a phonetic sign of the morpheme for each language. On the basis of second dictionary data, each constitution morpheme is replaced with a phonogram in a specific language corresponding to the phonetic sign specified in the S160 (S160). The second dictionary data is obtained by associating each phonetic sign with a phonogram in a specific language corresponding to the phonetic sign. According to the replaced phonogram, synthesized sound which utters the utterance content information in the specific language is generated and output (S250).SELECTED DRAWING: Figure 2

Description

  The present invention relates to a speech synthesizer that generates synthesized sound, and a program.

2. Description of the Related Art Conventionally, a singing synthesizer is known that sings a musical composition in which lyrics are assigned to musical notes composed of combinations of pitches and note values with synthesized sounds (see Patent Document 1).
In this type of synthesizer, in order to generate synthesized sound, a library that stores speech data necessary for speech synthesis and a synthesis engine that performs speech synthesis based on the speech data stored in the library are required. It becomes.

JP 2006-258846 A

By the way, there are cases where words in a plurality of languages are mixed in the lyrics in the music.
If words in a plurality of languages are mixed in the lyrics as described above, it is necessary to prepare a library and a synthesis engine for each language.

  In particular, the audio data stored in the library is preferably data generated from the same person. For this reason, if words in a plurality of languages are mixed in the utterance content information to be uttered, a lot of labor is required to secure data necessary for uttering the utterance content information.

In other words, the conventional technology has a problem that it is not possible to easily synthesize speech content in which words in a plurality of languages are mixed.
Therefore, an object of the present invention is to provide a technique for easily synthesizing speech content in which words of a plurality of languages are mixed.

One aspect of the present invention made to achieve the above object relates to a speech synthesizer including content acquisition means, language analysis means, replacement means, and synthesized sound output means.
The content acquisition means acquires utterance content information representing the wording of the content to be uttered. The language analysis means identifies the phonetic symbol of the constituent morpheme by collating the constituent morpheme with the first dictionary data. The first dictionary data referred to here is data in which each morpheme and a phonetic symbol of the morpheme are associated with each language. Further, the constituent morpheme is a morpheme constituting the utterance content information acquired by the content acquisition unit.

  Further, the replacement unit replaces each constituent morpheme with a phonetic character in a specific language corresponding to the phonetic symbol specified by the language analysis unit based on the second dictionary data. The second dictionary data referred to here is data in which each phonetic symbol is associated with a phonetic character in a specific language corresponding to the phonetic symbol.

Then, the synthesized sound output means generates and outputs a synthesized sound in which the utterance content information is uttered in a specific language according to the phonetic character replaced by the replacement means.
According to such a speech synthesizer, a constituent morpheme can be converted into a phonetic character of a specific language. That is, according to the speech synthesizer, even if words in a plurality of languages are mixed in the utterance content information, all words (morphemes) can be converted into phonetic characters in a specific language.

  Therefore, according to the speech synthesizer, it is possible to generate and output a synthesized sound of the utterance content information without preparing a library or a synthesis engine for each of a plurality of languages. In other words, according to the speech synthesizer, even if it is utterance content information in which words of a plurality of languages are mixed, a synthesized sound of the utterance content information can be easily generated.

In addition, the language analysis unit may determine whether the constituent morpheme is a morpheme of a specific language, and if the result of the determination is not a morpheme of the specific language, the linguistic symbol of the constituent morpheme may be specified.
According to such a speech synthesizer, a condition for specifying a phonetic symbol of a constituent morpheme can be a case where the constituent morpheme is a morpheme of a language other than the specific language. Thereby, according to the speech synthesizer, it is possible to reduce the number of times that the phonetic symbols of the constituent morphemes are specified in one utterance content information, and it is possible to reduce the amount of processing to be executed to specify the phonetic symbols of the constituent morphemes.

Furthermore, the language analysis means may determine whether the constituent morpheme is a morpheme of a specific language with Japanese as the specific language.
According to such a speech synthesizer, processing can be executed with Japanese as a specific language.

And the content acquisition means may acquire the lyrics which are the words assigned to at least some of the notes constituting the melody of the music as the utterance content information.
According to such a speech synthesizer, even if words of a plurality of languages (morphemes) are mixed in the lyrics of the music, the music can be sung by voice synthesis.

By the way, when the constituent morphemes of the utterance content information are converted into phonograms of a specific language, there is a possibility that the number of phonograms is larger than the number of target notes.
Therefore, the speech synthesizer as one aspect of the present invention may include a note dividing unit and an assigning unit.

  In this case, the note dividing means replaces each constituent morpheme with a phonetic character of a specific language by the replacing means, and as a result, the number of characters of the phonetic character is larger than the number of target notes to which the constituent morpheme is assigned. The target note is divided so as to match the number of phonetic characters. Then, the assigning means assigns a phonetic character to each note divided by the note dividing means.

Further, the synthesized sound output means may replace the phonetic character assigned to each note by the assigning means with the phonetic character replaced by the replacing means.
In such a speech synthesizer, one phonetic character can be assigned to one note. As a result, according to the speech synthesizer, the synthesized sound of the utterance content information can be made suitable for music and can be a synthesized sound with less discomfort.

Note that the present invention may be implemented as a program.
The program in this case causes the computer to execute a content acquisition procedure for acquiring utterance content information and a language analysis procedure for identifying phonetic symbols of the constituent morphemes by collating the constituent morphemes with the first dictionary data. Further, the program as one aspect of the present invention includes a replacement procedure for replacing each constituent morpheme with a phonetic character in a specific language corresponding to the phonetic symbol specified in the language analysis procedure based on the second dictionary data. And a synthesized sound output procedure for generating and outputting a synthesized sound in which the utterance content information is uttered in a specific language according to the replaced phonetic character.

  As described above, if the present invention is implemented as a program, it is used by loading the computer from a recording medium as necessary and starting it, or by acquiring it and starting it through a communication line as necessary. be able to. Then, by causing the computer to execute each procedure, the computer can function as a speech synthesizer.

  The recording medium referred to here includes, for example, a computer-readable electronic medium such as a DVD-ROM, a CD-ROM, and a hard disk.

It is a block diagram which shows schematic structure of a speech synthesis system. It is a flowchart which shows the process sequence of a reproduction | regeneration process. It is a flowchart which shows the process sequence of a specific language conversion process. It is explanatory drawing which shows the outline | summary of a specific language conversion process, (A) is a figure which shows an example of utterance content information, (B) is a figure which illustrates the condition which converted the lyric word into the phonetic symbol, C) is a diagram illustrating a situation where phonetic symbols are replaced with phonetic characters in a specific language. It is a flowchart which shows the process sequence of an utterance speed adjustment process. It is explanatory drawing explaining the outline | summary of an utterance speed adjustment process.

Embodiments of the present invention will be described below with reference to the drawings.
<Speech synthesis system>
A speech synthesis system 1 shown in FIG. 1 is a system that outputs a synthesized speech in which lyrics of a song specified by a user (hereinafter referred to as a target song) are sung as a guide vocal.

The speech synthesis system 1 includes an information processing server 10 and a karaoke device 30.
The information processing server 10 stores at least a MIDI music piece MD and dictionary data DD.

The karaoke apparatus 30 plays a MIDI music MD stored in the information processing server 10 and corresponding to the target music. Further, the karaoke apparatus 30 generates a synthesized voice in which the music is sung in accordance with the sound source data PD and outputs it as a guide vocal. Note that the speech synthesis system 1 includes a plurality of karaoke apparatuses 30.
<MIDI music>
The MIDI music MD is prepared in advance for each music, and has music data, lyrics data, and music information.

  Among these, the music data is data representing the score of one music according to the well-known MIDI (Musical Instrument Digital Interface) standard. This music data has at least a musical score track representing a musical score for each musical instrument used in the music.

  The musical score track defines at least a pitch (so-called note number) and a period during which the MIDI sound source outputs the performance sound (hereinafter referred to as a note length) for each performance sound output from the MIDI sound source. Yes. The note length in the score track is defined by the note-on timing of the performance sound and the note-off timing of the performance sound.

On the other hand, the lyric data is data relating to the lyrics of the music, and includes lyric text data and lyric output data. The lyric text data represents the lyrics of the music. The lyrics output data is data in which a timing correspondence relationship that associates the lyrics output timing, which is the output timing of characters constituting the lyrics (hereinafter referred to as “lyric constituent characters”), with the performance of the music data. In addition, the timing correspondence relationship stipulates that lyrics constituent characters are assigned to at least some of the performance sounds (that is, notes) constituting the main melody of the music.

  Furthermore, in the lyric data, character type information indicating the type of characters used for the lyric constituent characters is defined for each lyric constituent character. The character type mentioned here is information representing the language in which the character is used, and includes, for example, kanji, hiragana, katakana, latin, and arabic.

The music information is information related to the music, and includes identification information (that is, music ID) for identifying the music. In addition, the information related to the music referred to here includes, for example, a music title, an artist name, and lyrics language information indicating a language of lyrics.
<Dictionary data>
The dictionary data DD is data prepared for each language, and each morpheme, a phonetic symbol of the morpheme, and a phonetic character of a specific language corresponding to the phonetic symbol are associated with each other.

In the present embodiment, the language is a rule for expressing and transmitting information by voice or characters, such as Japanese, English, German, French, or Chinese. Further, the specific language is one specified language. In the present embodiment, Japanese is described as a specific language.
<Information processing server>
The information processing server 10 includes a communication unit 12, a storage unit 14, and a control unit 16.

  Among these, the communication unit 12 performs communication between the information processing server 10 and the outside via a communication network. That is, the information processing server 10 is connected to the karaoke apparatus 30 via a communication network. The communication network referred to here may be a wired communication network or a wireless communication network.

  The storage unit 14 is a known storage device configured to be able to read and write stored contents. The storage unit 14 stores a plurality of MIDI music pieces MD. 1 is an identifier for identifying the MIDI music piece MD stored in the storage unit 14 of the information processing server 10, and is assigned to each music piece. This code “n” is a natural number of 1 or more.

  Further, the storage unit 14 stores dictionary data DD. 1 is an identifier for identifying the dictionary data DD stored in the storage unit 14 of the information processing server 10, and is assigned for each language. This code “m” is a natural number of 2 or more.

The control unit 16 is a known control device that is configured around a known microcomputer including a ROM 18, a RAM 20, and a CPU 22. The ROM 18 stores processing programs and data that need to retain stored contents even when the power is turned off. The RAM 20 temporarily stores processing programs and data. The CPU 22 executes each process according to a processing program stored in the ROM 18 or the RAM 20.
<Karaoke equipment>
The karaoke apparatus 30 includes a communication unit 32, an input reception unit 34, a music playback unit 36, a storage unit 38, an audio control unit 40, a video control unit 46, and a control unit 50.

  In the communication unit 32, the karaoke apparatus 30 communicates with the outside via a communication network. The input receiving unit 34 is an input device that receives input of information and commands in accordance with external operations. The input device referred to here is, for example, a key, a switch, a reception unit of a remote controller, or the like.

  The music playback unit 36 performs a music performance based on the MIDI music MD downloaded from the information processing server 10. The music reproducing unit 36 is, for example, a MIDI sound source. The voice control unit 40 is a device that controls voice input / output, and includes an output unit 42 and a microphone input unit 44.

  A microphone 62 is connected to the microphone input unit 44. As a result, the microphone input unit 44 acquires the sound input via the microphone 62. A speaker 60 is connected to the output unit 42. The output unit 42 outputs the sound source signal of the music reproduced by the music reproducing unit 36 and the sound source signal of the singing sound from the microphone input unit 44 to the speaker 60. The speaker 60 outputs the sound source signal input from the output unit 42 instead of sound.

  The video control unit 46 outputs a video or an image based on the video data sent from the control unit 50. The video control unit 46 is connected to a display unit 64 that displays video or images.

  The storage unit 38 is a well-known storage device configured to be able to read and write stored contents. The storage unit 14 stores sound source data PD. The sound source data PD is data necessary for generation of synthesized speech (that is, speech synthesis). Specifically, the sound source data PD may be a speech unit or various parameters used for formant synthesis.

  The control unit 50 is configured around a known computer having at least a ROM 52, a RAM 54, and a CPU 56. The ROM 52 stores processing programs and data that need to retain stored contents even when the power is turned off. The RAM 54 temporarily stores processing programs and data. The CPU 56 executes each process according to a processing program stored in the ROM 52 or the RAM 54.

The ROM 52 of the present embodiment stores a processing program for the control unit 50 to execute the reproduction process.
<Reproduction processing>
Next, the reproduction process executed by the control unit 50 will be described.

This reproduction process is activated when the reproduction order of the target music is reached.
When the reproduction process is activated, as shown in FIG. 2, the control unit 50 first acquires the identification number (music ID) of the target music (S110). Subsequently, the control unit 50 acquires the lyrics data of the MIDI music MD including the music ID acquired in S110 from the information processing server 10 (S120). That is, in S120 of this embodiment, lyric data is acquired as utterance content information representing the wording of the content to be uttered.

  Then, the control unit 50 determines whether or not the lyrics expressed by the lyrics data acquired in S120 (hereinafter referred to as “target lyrics”) is a specific language based on the music information (S130).

As a result of the determination in S130, when the target lyrics are not a specific language (S130: NO), the control unit 50 shifts the reproduction process to S200 described later in detail. Specifically, in S130 of the present embodiment, if the lyrics language information included in the music information is a specific language, it is determined that the target lyrics are the specific language. In the present embodiment, as a state where the lyric language information is a specific language, when the lyric word of the specific language and the lyric word other than the specific language are mixed, the ratio of the lyric word of the specific language is Including that the ratio is equal to or greater than a predetermined ratio. The lyric word mentioned here is a morpheme constituting the target lyrics, and is an example of a constituent morpheme described in the claims.

  On the other hand, as a result of the determination in S130, if the target lyrics are a specific language (S130: YES), the control unit 50 extracts one lyrics word from all the lyrics words constituting the target lyrics (S140). ). In S <b> 140, the control unit 50 may extract lyrics words along with the progress of time in the target music. Hereinafter, the lyric word extracted in S140 is referred to as a target word.

  Subsequently, the control unit 50 determines whether or not the target word is represented by characters other than those used in the specific language (S150). As a result of the determination in S150, if the target word is not represented by characters other than those used in the specific language, that is, represented by characters (for example, hiragana, katakana, kanji) used in the specific language. If so (S150: NO), the controller 50 shifts the reproduction process to S160. In S150 of the present embodiment, the control unit 50 makes a negative determination in S150 if the character type information included in the lyrics data represents a character used in a specific language.

  In S <b> 160, the control unit 50 identifies the phonetic character in the specific language for the target word from the dictionary data DD, and replaces the target word with the phonetic character in the specific language. Thereafter, the control unit 50 shifts the reproduction process to S180 described later in detail.

  On the other hand, as a result of the determination in S150, if the target word is represented by characters other than those used in the specific language (for example, Latin characters, Arabic characters, traditional characters, etc.) (S150: YES), the control unit 50 Shifts the reproduction process to S170.

In S170, the control unit 50 executes a specific language conversion process for converting the target word into a phonetic character of a specific language. Details of the specific language conversion process will be described later.
Furthermore, the control unit 50 performs a speech rate adjustment process for assigning each phonogram included in the target word to one note (S180). Details of this speech rate adjustment process will be described later.

  Subsequently, the control unit 50 determines whether or not the steps of S140 to S180 have been executed for all lyrics words constituting the target lyrics (S190). As a result of the determination in S190, if the steps of S140 to S180 are not executed for all the lyrics words (S190: NO), the control unit 50 returns the reproduction process to S140. In S140, the control unit 50 extracts a new lyric word as a target word, and executes steps S150 to S190.

  On the other hand, as a result of the determination in S180, if the steps of S140 to S180 are executed for all the lyrics words (S190: YES), the control unit 50 shifts the reproduction process to S240 described later in detail. Let

  By the way, in S200 which transfers to the case where object lyrics are not a specific language (S130: NO), the control part 50 extracts one lyrics word from all the lyrics words which comprise object lyrics. In S <b> 200, the control unit 50 may extract a lyric word along with the progress of time in the target song. In the following, one lyric word extracted in S200 is also referred to as a target word.

Subsequently, the control unit 50 executes a specific language conversion process (S210). Further, the control unit 50 executes a speech rate adjustment process (S220). Subsequently, the control unit 50 determines whether or not the steps of S200 to S220 have been executed for all the lyrics words constituting the target lyrics (S230).

  As a result of the determination in S230, if the steps of S200 to S230 are not executed for all lyrics words (S230: NO), the control unit 50 returns the reproduction process to S200. In S200, the control unit 50 extracts a new lyric word as a target word and executes the steps from S210 to S230.

  On the other hand, as a result of the determination in S230, if the steps of S200 to S220 are executed for all the lyrics words (S230: YES), the control unit 50 shifts the reproduction process to S240.

  In S240, the control unit 50 acquires the MIDI music MD corresponding to the music ID acquired in S110 from the information processing server 10, and reproduces the target music. By this S240, the performance sound of the target music is emitted from the speaker 60.

  Further, in the reproduction process, the control unit 50 generates and outputs a guide vocal that accurately sings the target lyrics of the target music according to the sound source data PD stored in the storage unit 38 (S250). In S250, the control unit 50 synthesizes the target lyrics expressed only by the phonetic characters in the specific language according to the phonetic characters. In the present embodiment, the speech synthesis may be realized by a known method such as waveform connection or formant synthesis. By this S250, the guide vocal is emitted from the speaker 60.

Thereafter, the reproduction process ends.
<Specific language conversion processing>
Next, the specific language conversion process activated in S170 and S210 of the reproduction process will be described.

  In this specific language conversion process, as shown in FIG. 3, the control unit 50 selects one dictionary data DD from the dictionary data DD stored in the storage unit 14 of the information processing server 10, and the target word Are collated (S310). Hereinafter, the dictionary data DD selected in S310 is referred to as target dictionary data.

  As a result of the collation in S310, if a morpheme that matches the target word does not exist in the target dictionary data DD (S320: NO), the control unit 50 returns the specific language conversion process to S310. In S310, new dictionary data DD is selected as target dictionary data DD, and the target word is collated.

  On the other hand, as a result of the collation in S310, if a morpheme that matches the target word exists in the target dictionary data DD (S320: YES), the control unit 50 shifts the specific language conversion process to S330. In S330, the control unit 50 converts the target word into a phonetic symbol based on the target dictionary data DD. Specifically, in S330, the control unit 50 specifies a phonetic symbol corresponding to the target word (ie, morpheme) from the target dictionary data DD as shown in FIGS. 4 (A) and 4 (B). Convert the target word into phonetic symbols.

  Further, in the specific language conversion process, the control unit 50 replaces the target word converted into a phonetic symbol in S330 with a phonetic character in the specific language (S340). Specifically, in S340, as shown in FIG. 4C, the control unit 50 specifies a phonetic character in a specific language for the target word from the target dictionary data DD, and specifies the target word as a phonetic character in the specific language. Replace with In the present embodiment, it is conceivable to use katakana as phonetic characters in a specific language.

Thereafter, the control unit 50 ends the specific language conversion process, and returns the process to S180 or S220 of the reproduction process.
That is, in the specific language conversion process, a lyric word expressed in a language other than the specific language is replaced with a phonogram of a specific language having an utterance form similar to the utterance form of the pronunciation symbol of the lyric word.
<Voice rate adjustment processing>
Next, the speech rate adjustment process activated in the reproduction processes S180 and S220 will be described.

  When this utterance speed adjustment process is activated, as shown in FIG. 5, the control unit 50 determines whether or not the number of characters of the target word replaced with the phonetic character of the specific language is one character. (S410). As a result of the determination in S410, if the number of characters is one (S410: YES), the control unit 50 shifts the utterance speed adjustment processing to S420.

  In S420, the control unit 50 assigns one phonetic character representing the target word to one note to which the target word is assigned. Thereafter, the control unit 50 ends the speech rate adjustment process and returns the process to S190 or S230 of the reproduction process.

  On the other hand, as a result of the determination in S410, if the number of characters of the target word replaced with the phonetic character in the specific language is not one character (S410: NO), the control unit 50 advances the utterance speed adjustment processing to S430. Transition. In S430, the control unit 50 acquires information on a note (hereinafter referred to as a target note) to which the target word is assigned from the MIDI music piece MD. The target note information acquired in S430 is the type of note such as a quarter note or an eighth note, or the note value of the note.

  In the utterance speed adjustment processing, the control unit 50 divides the target note so that the number of notes matches the number of phonograms representing the target word (S440). Further, in the utterance speed adjustment process, the control unit 50 assigns each phonogram representing the target word to each of the target notes divided in S440 (S450).

Thereafter, the control unit 50 ends the utterance speed adjustment process and returns the process to S190 or S230 of the reproduction process.
That is, in the utterance speed adjustment process, as shown in FIG. 6, when the number of phonograms representing the target word is larger than the number of target notes to which the target word is assigned, the phonogram representing the target word The target note is divided so as to match the number of characters. In the utterance speed adjustment process, each of the phonetic characters representing the target word is assigned to each divided note.
[Effect of the embodiment]
As explained above, according to the karaoke apparatus 30, a lyric word can be converted into a phonetic character of a specific language. That is, according to the karaoke apparatus 30, even if words in a plurality of languages are mixed in the target lyrics, all the words (morphemes) can be converted into phonetic characters in a specific language.

For this reason, according to the karaoke apparatus 30, it is possible to generate and output a synthesized sound of the target lyrics without preparing a library or a synthesis engine for each of a plurality of languages.
In other words, according to the karaoke apparatus 30, a synthesized sound of the utterance content information can be easily generated even for target lyrics in which words in a plurality of languages are mixed.

In the reproduction process, the condition for specifying the phonetic symbol of the target word is a case where the target word is a morpheme of a language other than the specific language.
As a result, according to the playback process, the number of executions of specifying the phonetic symbol of the target word and replacing it with a phonetic character in a specific language can be reduced in one target lyrics, specifying the phonetic symbol of the target word and the specific language It is possible to reduce the amount of processing for executing the replacement with the phonetic character.

By the way, when the lyrics word of the target lyric is converted into a phonetic character of a specific language, the number of characters of the phonetic character may be larger than the number of target notes.
Even in such a case, in the reproduction process of the present embodiment, one phonetic character is assigned to one note in the utterance speed adjustment process. As a result, according to the reproduction process, the synthesized sound in which the lyrics of the target song are sung can be made suitable for the song, and the synthesized sound with less sense of incongruity can be obtained.
[Other Embodiments]
As mentioned above, although embodiment of this invention was described, this invention is not limited to the said embodiment, In the range which does not deviate from the summary of this invention, it is possible to implement in various aspects.

  For example, in the reproduction process of the above embodiment, the lyrics data is acquired as the utterance content information, but the utterance content information is not limited to this. That is, the utterance content information may be literature or other content as long as it is information representing the wording of the content to be uttered.

In the above embodiment, Japanese is the specific language, but the specific language in the present invention is not limited to this, and any language may be the specific language.
Furthermore, in the dictionary data DD in the above embodiment, each morpheme, a phonetic symbol of the morpheme, and a phonetic character in a specific language corresponding to the phonetic symbol are associated. The structure of this dictionary data is However, it is not limited to this. For example, the dictionary data includes first dictionary data in which each morpheme is associated with a phonetic symbol of the morpheme, and second data in which each phonetic symbol is associated with a phonetic character of a specific language corresponding to the phonetic symbol. Dictionary data may be provided.

  In the above embodiment, the sound source data PD is stored in the storage unit 38 of the karaoke apparatus 30. However, in the present invention, the sound source data PD may not be stored in the storage unit 38 of the karaoke apparatus 30. It may be stored in the information processing server 10.

  Further, in the above embodiment, the main body that executes the playback process is the karaoke apparatus 30, but the main body that executes the playback process is not limited to this, and is an information processing apparatus such as a personal computer or a smart phone. Also good.

  The present invention can be realized in various forms such as a program for causing a computer to function as the karaoke device, a recording medium on which the program is recorded, in addition to the karaoke device (speech synthesizer) described above.

In addition, the aspect which abbreviate | omitted a part of structure of the said embodiment is also embodiment of this invention. Further, an aspect configured by appropriately combining the above embodiment and the modification is also an embodiment of the present invention. Moreover, all the aspects which can be considered in the limit which does not deviate from the essence of the invention specified by the wording described in the claims are the embodiments of the present invention.
[Correspondence between Embodiment and Claims]
Finally, the relationship between the description of the above embodiment and the description of the scope of claims will be described.

The function obtained by executing S120 in the reproduction process of the above embodiment is an example of the content acquisition unit described in the claims, and the function obtained by executing S310 to S330 of the specific language conversion process Is an example of the language analysis means described in the claims. Further, the function obtained by executing S340 of the specific language conversion process is an example of the replacement means described in the claims, and the function obtained by executing S250 of the reproduction process is claimed. It is an example of the synthetic | combination sound output means described in the range.

  Furthermore, the function obtained by executing S440 of the utterance speed adjustment process is an example of the note dividing means described in the claims, and the function obtained by executing S450 is included in the claims. It is an example of the described allocation means.

  DESCRIPTION OF SYMBOLS 1 ... Speech synthesis system 10 ... Information processing server 12 ... Communication part 14 ... Memory | storage part 16 ... Control part 18,52 ... ROM 20,54 ... RAM 22,56 ... CPU 30 ... Karaoke apparatus 32 ... Communication part 34 ... Input reception part 36 ... Music reproduction unit 38 ... Storage unit 40 ... Audio control unit 42 ... Output unit 44 ... Microphone input unit 46 ... Video control unit 50 ... Control unit 60 ... Speaker 62 ... Microphone 64 ... Display unit

Claims (6)

Content acquisition means for acquiring utterance content information representing the wording of the content to be uttered;
By comparing each morpheme and the phonetic symbol of the morpheme for each language, by comparing the constituent morpheme that is the morpheme constituting the utterance content information acquired by the content acquisition unit, Language analysis means for identifying phonetic symbols;
Based on the second dictionary data in which each of the phonetic symbols is associated with a phonetic character of a specific language corresponding to the phonetic symbol, the phonetic in a specific language corresponding to the phonetic symbol specified by the language analyzing means Replacement means for replacing each of the constituent morphemes into characters,
A speech synthesizer comprising: synthesized sound output means for generating and outputting a synthesized sound produced by uttering the utterance content information in a specific language according to the phonetic character replaced by the replacement means. The language analysis means includes
It is determined whether or not the constituent morpheme is a morpheme of the specific language, and if the result of the determination is not a morpheme of the specific language, a phonetic symbol of the constituent morpheme is specified. The speech synthesizer described. The language analysis means includes
The speech synthesis apparatus according to claim 1, wherein Japanese is used as the specific language, and it is determined whether or not the constituent morpheme is a morpheme of the specific language. The content acquisition means includes
The lyric that is a word assigned to at least some of the notes constituting the melody of the music is acquired as the utterance content information. The speech synthesis apparatus according to one item. When the number of characters of the phonetic character is greater than the number of target notes to which the constituent morpheme is assigned as a result of replacing the constituent morphemes with the phonetic characters of the specific language by the replacement means, Note dividing means for dividing the target note so as to match the number of characters,
Assigning means for assigning the phonogram to each note divided by the note dividing means;
The synthetic sound output means includes
The phonetic character according to any one of claims 1 to 4, wherein each phonetic character assigned to each note by the assigning unit is a phonetic character replaced by the replacing unit. Synthesizer. A content acquisition procedure for acquiring utterance content information representing the wording of the content to be uttered;
By comparing each morpheme and a phonetic symbol of the morpheme for each language, by comparing the constituent morpheme that is the morpheme constituting the utterance content information acquired in the content acquisition procedure, Language analysis procedure to identify phonetic symbols;
Based on the second dictionary data in which each of the phonetic symbols is associated with a phonetic character in a specific language corresponding to the phonetic symbol, the phonetic in a specific language corresponding to the phonetic symbol specified in the language analysis procedure A replacement procedure for replacing each of the constituent morphemes into characters,
A program for causing a computer to execute a synthetic sound output procedure for generating and outputting a synthetic sound produced by uttering the utterance content information in a specific language according to the phonetic character replaced in the replacement procedure.