JP2009251015A - Voice edition program, voice edition system, semiconductor integrated circuit device, and manufacturing method for semiconductor integrated circuit device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To efficiently edit a voice data file required and sufficient for speaking a voice guide message. <P>SOLUTION: A computer is functioned as a phrase data storage part 172 storing a phrase data including a voice data of phrases and a text data of the phrases, a sentence editing part 120 for edition-processing a sentence, and a sentence information generation-processing part 122 for generating sentence information including phrase specifying information for specifying the phrases constituting the sentence and sequence information as to a regeneration order of the phrases. The sentence information generation-processing part 122 receives the text data of the sentence, executes sentence division processing for dividing the text data of the received sentence into the plurality of phrases, and generates the phrase specifying information and the sequence information of the phrases constituting the divided sentence. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a voice editing program, a voice editing system, a semiconductor integrated circuit device, and a method for manufacturing a semiconductor integrated circuit device.

2. Description of the Related Art There is known an electronic device that includes a host processor and an audio IC, and is mounted with an audio playback system in which the host processor and the audio IC work in conjunction with each other to mainly send messages by voice.
JP 2002-55692 A

  When an electronic device has a voice function for outputting a voice guide message set in advance as a user interface, a voice data file corresponding to the voice guide message to be output is stored in the built-in ROM of the voice playback device, There is an audio reproduction system that reproduces and outputs audio data read from a built-in ROM based on a command.

  In such an audio reproduction system, once the contents of the internal ROM are determined, it is difficult to change, add or modify. Therefore, it is possible to store the audio data file in the internal ROM after sufficiently confirming the voice of the audio guide message. preferable.

  Further, when a plurality of voice guide messages are scheduled to be uttered, it is preferable that all voice files necessary and sufficient for reproducing the plurality of voice guide messages are stored without fail.

  The present invention has been made in view of the technical problems as described above, and an object of the present invention is to efficiently generate a voice data file necessary and sufficient to utter a voice guide message to be output by an electronic device or the like. The present invention relates to a voice editing program, a voice editing system, a semiconductor integrated circuit device, and a method for manufacturing a semiconductor integrated circuit device, which are often edited and generated.

(1) The present invention
A program that allows a computer to function as a voice editing tool,
A phrase data storage unit storing phrase data including phrase voice data and phrase text data;
A sentence editing processing unit that performs sentence editing processing based on the phrase data;
Based on the sentence editing process result, the sentence function generation processing unit for generating sentence information including phrase specifying information for specifying a phrase constituting the sentence and sequence information regarding the reproduction order of the phrases, and causing the computer to function,
The sentence editing processing unit
The sentence text data is received, and based on the phrase text data, sentence split processing is performed to divide the received sentence text data into a plurality of phrases,
The sentence information generation processing unit
Sentence information including phrase specifying information and sequence information of phrases constituting the divided sentence is generated.

  A phrase is, for example, a phrase or a part of a sentence. The sound data is a sound data file reproduced by an existing sound reproduction system, and may be a compressed sound file. For example, audio data created by a TTS tool may be used.

  The sentence is, for example, a sentence, and may be a sentence used as a voice guide message for an electronic device or the like.

  The phrase text data is text data indicating how to read and write the phrase, and may be character (code indicating kana characters, kana characters, kanji characters, or numbers) data.

  Phrase data stored in the phrase data storage unit may include phrase audio file size information (number of bytes, etc.), phrase audio file playback time information (ms), and the like.

  The phrase specific information is information accessible to the file information of the audio data corresponding to the phrase, and may be, for example, a file name of the audio data file, an identification ID of the phrase data, or an index to the phrase data.

  The sentence information may be information in which file information (file names) of phrase voice data is arranged according to sequence information.

  The sentence division process is a process of comparing and collating the text data constituting the sentence with the text of the phrase and the data, and dividing the text data constituting the sentence into the text data of the phrase. The text data constituting the sentence is a first text part, a second text part,. When divided into the nth text part, the first text part, the second text part,... The division process may be performed when all of the nth text portion matches the phrase text data stored in the phrase data storage unit as the phrase text data.

  The present invention can efficiently edit and generate necessary and sufficient voice data to utter a sentence voice such as a voice guide message.

(2) This program
A phrase editing information generation processing unit may be included that generates editing information of a phrase that constitutes the sentence based on a sentence editing process result, and stores the generated phrase editing information in association with the phrase data.

  The phrase editing information may include, for example, usage count information used for sentences and information on whether or not data is written to the ROM.

  The phrase editing information processing unit may count up the value of the usage count information corresponding to the phrase constituting the sentence analysis when the sentence information is created.

  The information on the presence or absence of writing to the ROM is information for designating whether or not to write to the memory storing the voice data file of the voice guide message. Here, it is used for the sentence by designating that there is writing to the ROM. Voice data of phrases that have not been recorded can also be stored in the memory.

(3) This program
The phrase editing information generation processing unit
The number of times of use of a phrase used in a plurality of sentences or a phrase used a plurality of times in one sentence may be counted, and the count value may be held as phrase editing information.

  For example, for a given phrase, a plurality of audio data files having different sound quality (audio data files having different file sizes) are prepared, and different sound quality audio data files are used according to the count value of the number of times the phrase is used. You may do it. For example, a high-quality voice data file may be used for a frequently used phrase. By doing in this way, sound quality can be improved efficiently.

(4) This program
Memory writing information for extracting a storage target phrase to be stored in the audio data memory based on the phrase editing information, reading out the audio data of the extracted phrase from the phrase data storage unit, and writing to the audio data memory based on the read audio data Including a memory write information generation unit for generating
For phrases used in a plurality of sentences, memory write information may be generated so that the same audio data is not written redundantly.

When the phrase editing information is, for example, information on the number of times of use used in a sentence or information on the presence / absence of writing to a ROM, the information on the number of times of use information is one or more and the information on whether or not writing to the ROM is written A phrase that is present may be extracted.
Since extraction is performed in units of phrases based on the phrase editing information, it is possible to generate memory writing information (ROM image) so that the same audio data is not written redundantly for phrases used in a plurality of sentences.

  Therefore, even for a phrase shared by a plurality of sentences, only one phrase voice data is stored in the memory, so that an increase in memory size can be prevented.

(5) This program
The memory write information generation unit
The total size of the memory write information may be calculated and the size information may be output based on the calculation result.

  The memory size information to be used may be compared with the total size, and the comparison result may be output. Warning information may be output when the memory size information to be used is a climber group smaller than the total size.

(6) This program
The sentence editing processing unit
Accepts phrase selection input stored in the phrase data storage unit, performs phrase combination processing to create a sentence based on the selected phrase,
The sentence information generation processing unit
You may generate | occur | produce the sentence information containing the phrase specific information and sequence information of the phrase which comprises the created sentence.

(7) This program
The sentence editing processing unit
Based on the result of the phrase division process, a display output process for displaying a phrase constituting the sentence may be performed.

  As a display output, for example, a sentence-format sentence display screen may be generated, and a sentence and a plurality of phrases constituting the sentence extracted as a result of sentence division may be displayed.

  Further, for example, when an input sentence has an error and cannot be divided into phrases, the phrase constituting the sentence may not be displayed. In this way, the division result is easy to understand and can be easily corrected.

(8) This program
The text data of the sentence includes delimiter data indicating phrase delimiters,
The sentence editing processing unit
The sentence dividing process may be performed based on the delimiter data.

  The delimiter data may be space data, for example, or text data indicating a predetermined character or symbol.

  If it does in this way, it can have a avoidance means in the case where a phrase division is recognized by mistake in phrase division processing. Separation data (such as a space) may be inserted in advance at a position in the sentence where the division is desired.

  For example, there is phrase data for a phrase with a duplicated sentence such as “Turn off power”, “Turn off power”, “Turn off”, “Please”, etc. In some cases, the sentence can be expanded to the intended phrase by clearly indicating the place where you want to turn it off, such as "Please turn off the power".

(9) This program
Sentence voice playback output processing for reading out voice data corresponding to a phrase constituting the sentence from the phrase data storage unit based on specific information of the phrase constituting the sentence and reproducing and outputting the voice data read according to the sequence information of the sentence information Part may be included.

  In this way, an optimum silent section can be set by changing the setting of the waiting time as needed while confirming the voice of the sentence in which the edited waiting time is set.

(10) This program
The sentence editing processing unit
Edit input related to waiting time information related to the length of the silent section set for at least one of the phrases constituting the sentence and between the phrases,
The sentence information generation processing unit
Sentence information including the waiting time information may be generated.

  The sentence information may be information in which file information (file name) of phrase voice data and waiting time information set before or between phrases are arranged according to sequence information.

(11) This program
The sentence audio reproduction output processing unit
Based on the waiting time information of the sentence information, a silent section may be set before the phrase or between the phrases to reproduce and output the voice data.

(12) This program
The sentence editing processing unit
A sentence edit screen display control unit for controlling display of a sentence edit screen for editing a sentence;
The sentence edit screen display control unit
The sentence and the phrase constituting the sentence are displayed in a tabular form, and each column includes a sentence display field, a phrase display field constituting the sentence, and a silence interval setting field provided between phrases or in front of the phrase. The section setting field may be provided between the phrase display field and the phrase display field.

(13) This program
A sentence voice playback command generation processing unit for generating a sentence voice playback command for instructing to play back voice data necessary for playback of the sentence voice from the voice data memory in an order corresponding to the read sentence based on the sentence information; But you can.

  For example, the voice data file of the phrase to be read may be determined based on the phrase specifying information of the sentence information, and the sentence voice reproduction command may be generated by arranging the file names of the voice data according to the sequence information of the sentence information.

The sentence voice playback command generation processing unit
Based on the waiting time information of the sentence information, a sentence voice playback command including the waiting time information may be generated so as to reproduce and output the voice of the voice data by setting a silent section before the phrase or between the phrases. Good.

  In this case, the sentence audio reproduction command may be generated by arranging the hourly information and the file name according to the reproduction order.

(14) The present invention provides:
An audio editing system,
A phrase data storage unit storing phrase data including phrase voice data and phrase text data;
A sentence editing processing unit that performs sentence editing processing based on the phrase data;
A sentence information generation processing unit for generating sentence information including phrase specifying information for specifying phrases constituting the sentence and sequence information related to the reproduction order of the phrases based on a sentence editing process result;
The sentence editing processing unit
The sentence text data is received, and based on the phrase text data, sentence split processing is performed to divide the received sentence text data into a plurality of phrases,
The sentence information generation processing unit
Sentence information including phrase specifying information and sequence information of phrases constituting the divided sentence is generated.

(15) The present invention provides:
A method of manufacturing a semiconductor integrated circuit device for speech synthesis, including a non-volatile storage unit,
Storing phrase data including phrase voice data and phrase text data in a phrase data storage unit;
A sentence editing processing unit step for performing sentence editing processing based on the phrase data;
Sentence information generation processing step for generating sentence information including phrase specifying information for specifying phrases constituting the sentence and sequence information regarding the playback order of phrases based on the sentence editing processing result, and voice based on the phrase editing information A memory write information generation step of extracting a storage target phrase to be stored in the data memory, reading out the voice data of the extracted phrase from the phrase data storage unit, and generating memory write information to be written in the voice data memory;
Writing the memory write information to be written into the nonvolatile storage unit,
Including
In the sentence editing process step,
The sentence text data is received, and based on the phrase text data, sentence split processing is performed to divide the received sentence text data into a plurality of phrases,
In the sentence information generation processing step,
Generate sentence information including the phrase identification information and sequence information of the phrases that make up the divided sentence,
For phrases used in a plurality of sentences, memory write information is generated so that the same audio data is not written redundantly.

(16) The present invention provides:
A non-volatile storage unit that stores memory write information generated by the voice editing program according to any one of the above,
A voice synthesizer that receives sentence information or a sentence voice reproduction command, reads out voice data from the nonvolatile storage unit based on the received sentence information or sentence voice reproduction command, and reproduces and outputs a voice guide message corresponding to the sentence;
Is a semiconductor integrated circuit device.

  DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the drawings. The embodiments described below do not unduly limit the contents of the present invention described in the claims. Moreover, not all of the configurations described below are essential constituent requirements of the present invention.

1. Configuration FIG. 1 is an example of a functional block diagram of a voice editing system according to the present embodiment.
Note that the voice editing system 100 according to the present embodiment does not have to include all of the components (each unit) in FIG. 1 and may have a configuration in which some of them are omitted.

  The operation unit 160 is for inputting a user operation or the like as data, and the function can be realized by hardware such as an operation button, an operation lever, a touch panel, or a microphone.

  The storage unit 170 serves as a work area for the processing unit 110, the communication unit 196, and the like, and its function can be realized by hardware such as a RAM.

  The storage unit 170 may function as a phrase data storage unit 172 in which phrase data including phrase voice data and text data related to phrase reading is stored. Phrase data including phrase voice data and phrase text data may be stored as the phrase data.

  The storage unit 170 may function as a sentence information storage unit 174 that stores sentence information including file information (file name) of audio data of phrases constituting a sentence and sequence information related to the reproduction order of phrases.

  In addition, the storage unit 170 may function as a phrase editing information storage unit 176 that holds the editing information (the number of times of use, whether or not to write to the ROM) of the phrase constituting the sentence in association with the phrase data.

  The information storage medium 180 (a computer-readable medium) stores programs, data, and the like, and functions as an optical disk (CD, DVD, etc.), a magneto-optical disk (MO), a magnetic disk, a hard disk, and a magnetic disk. It can be realized by hardware such as a tape or a memory (ROM).

  The information storage medium 180 stores a program for causing the computer to function as each unit of the present embodiment and auxiliary data (additional data), and also functions as a phrase database or a phrase data storage unit 182 read from the phrase database. Note that the information storage medium 180 may also store ROM images and voice playback commands generated by this system.

  The processing unit 100 performs various processes of the present embodiment based on a program (data) stored in the information storage medium 180, data read from the information storage medium 180, and the like. That is, the information storage medium 180 stores a program for causing a computer to function as each unit of the present embodiment (a program for causing a computer to execute processing of each unit).

  The display unit 190 outputs an image generated according to the present embodiment, and functions thereof are a CRT display, an LCD (liquid crystal display), an OELD (organic EL display), a PDP (plasma display panel), and a touch panel display. It can be realized by hardware such as. The editing screen and dialog screen of this tool are displayed on the display.

  The sound output unit 192 outputs the synthesized speech generated by the present embodiment, and the function can be realized by hardware such as a speaker or headphones.

  The communication unit 196 performs various controls for communicating with the outside (for example, a host device or another terminal), and functions thereof include hardware such as various processors or communication ASICs, It can be realized by a program.

  Note that a program (data) for causing a computer to function as each unit of the present embodiment is transferred from the information storage medium included in the host device (server device) to the information storage medium 180 (or storage unit 170) via the network and communication unit 196. You may make it deliver. Use of the information storage medium of such a host device (server device or the like) can also be included in the scope of the present invention.

  The non-volatile storage unit 150 is configured by a storage medium that functions as a non-volatile memory, and may be a ROM used as a built-in ROM of a speech synthesis IC incorporated in an electronic device, for example. The memory write information 152 may be written in the nonvolatile storage unit 150. Further, a sentence reproduction command may be written in the nonvolatile storage unit 150.

  The processing unit 110 (processor) performs various processes using the storage unit 170 as a work area based on operation data, a program, and the like from the operation unit 160. The functions of the processing unit 110 can be realized by hardware such as various processors (CPU, DSP, etc.), ASIC (gate array, etc.), and programs.

  The processing unit 110 includes a phrase editing processing unit 120, a sentence information generation processing unit 122, a phrase information generation processing unit 124, a memory writing information generation unit 130, a sentence voice reproduction command generation unit 132, and a sentence voice reproduction output processing unit 140. May be included.

  The sentence editing processing unit 120 performs sentence editing processing based on the phrase data, and the sentence information generation processing unit 122 performs phrase specifying information for specifying a phrase constituting the sentence and a phrase based on the sentence editing processing result. Sentence information including sequence information related to the reproduction order is generated.

  The sentence editing processing unit 120 receives sentence text data, performs sentence division processing for dividing the received sentence text data into a plurality of phrases based on the phrase text data, and the sentence information generation processing unit 122 is divided. Sentence information including phrase specifying information and sequence information of phrases constituting a sentence is generated.

  The phrase editing information generation processing unit 124 generates the editing information of the phrase constituting the sentence based on the sentence editing processing result, and holds the generated phrase editing information in association with the phrase data.

  The phrase editing information generation processing unit 124 may count the number of times a phrase used in a plurality of sentences or a phrase used a plurality of times in one sentence and hold the count value as phrase editing information.

  The memory writing information generation unit 130 extracts a storage target phrase to be stored in the audio data memory based on the phrase editing information, reads out the audio data of the extracted phrase from the phrase data storage unit, and based on the read audio data, Memory write information to be written to the audio data memory is generated. Therefore, memory writing information is generated so that the same audio data is not written redundantly for phrases used in a plurality of sentences.

  The memory write information generation unit 130 may calculate the total size of the memory write information and output size information based on the calculation result.

  The sentence editing processing unit 120 receives a selection input of a phrase stored in the phrase data storage unit, performs a phrase combining process for creating a sentence based on the selected phrase, and the sentence information generation processing unit 122 You may make it produce | generate the sentence information containing the phrase specific information and sequence information of the phrase which comprises a sentence.

  In addition, the sentence editing processing unit 120 may perform display output processing for displaying a phrase constituting the sentence based on the phrase division processing result.

  The sentence text data may include delimiter data indicating phrase delimiters, and the sentence editing processing unit 120 may perform the sentence dividing process based on the delimiter data.

  The sentence sound reproduction output processing unit 140 reads out the sound data corresponding to the phrase constituting the sentence from the phrase data storage unit based on the specific information of the phrase constituting the sentence, and the sound of the sound data read according to the sequence information of the sentence information Is played back.

  In addition, the sentence editing processing unit 120 accepts an editing input related to waiting time information regarding the length of a silent section set for at least one of the phrases constituting the sentence and between the phrases, and the sentence information generating processing unit 122 receives the waiting information. Sentence information including time information may be generated.

  Further, the sentence sound reproduction output processing unit 140 may reproduce and output the sound of the sound data by setting a silent section before the phrase or between the phrases based on the waiting time information of the sentence information.

  In addition, the sentence editing processing unit 120 may include a sentence editing screen display control unit (not shown) that performs display control of a sentence editing screen for editing a sentence. The sentence edit screen display control unit displays sentences and phrases constituting the sentence in a table format, and each column includes a sentence display field, a phrase display field that constitutes the sentence, and a silence provided between phrases or before the phrase. The silent section setting field may be provided between the phrase display field and the phrase display field.

  The sentence voice reproduction command generation processing unit 132 generates a sentence voice reproduction command for instructing to reproduce the voice data necessary for reproducing the sentence voice from the voice data memory in the order corresponding to the read sentence based on the sentence information. May be.

  FIG. 2 is a diagram for explaining the phrase data and the phrase editing information.

  The phrase data 200 includes phrase audio data 202, an audio data file name 204 (phrase audio data file information) in which the phrase audio data 202 is stored, and audio log information 210 corresponding to the phrase audio data 202. It may be stored in association with the phrase identification ID 206.

  The audio data 202 is a sound data file that can be reproduced by an existing audio reproduction system, and may be a compressed sound file. For example, audio data created by a TTS tool may be used.

  The audio data file name 204 only needs to be file information related to the audio data of the phrase, and may be information accessible to the audio file such as file identification information of the audio file of the phrase and index information to the audio file.

  The audio log information 210 may include text information 212 that is text data related to phrase reading. The audio log information 210 may also include file size information (such as the number of bytes) 214 in which phrase audio data is stored. The audio log information 210 may also include playback time information (ms) 216 of the phrase audio file. The audio log information 210 may also include other information (not shown) such as TTS parameters and data format information.

  The phrase editing information 220 is editing information generated and generated for each phrase based on the result of the sentence editing process of the present embodiment, and is held in association with the phrase data 200. The phrase editing information 220 may include usage count information 222 used for sentences. The phrase editing information 220 may include ROM writing information 224 for instructing whether or not to write to the ROM.

  FIG. 3 is a diagram for explaining sentence information.

  The sentence information 240 is information generated based on the sentence editing process result, and may be stored in association with the sentence identification ID 242.

  The sentence information 240 may include text information 244 of phrases constituting the sentence.

  The sentence information 240 may include sentence size information 246. The sentence size information 244 may be the total number of bytes of the audio data file of the phrase constituting the sentence. In addition, when the waiting time is included as silent voice data, the total number of bytes including the silent section data may be used.

  The sentence information 240 may include sentence playback time information 248. The sentence playback time information 248 may be the total playback time of the audio files of the phrases constituting the sentence. Moreover, the total time including the waiting time set before and after the phrase or between the phrases may be used.

  The sentence information 240 may include comment information 250 that has received an edit input related to the sentence.

  The sentence information 240 may include phrase specifying information 254-1 to 254-n constituting the sentence. The phrase specifying information 254-1 to 254-n is information accessible to the file information of the voice data (202 in FIG. 2) corresponding to the phrase, and may be, for example, the file name of the voice data file (204 in FIG. 2). Alternatively, the phrase identification ID (206 in FIG. 3) may be used. The phrase specifying information 254-1 to 254-n may be arranged according to the playback order of phrases (the index n matches the playback order of phrases).

  The sentence information 240 may include waiting time information 252-1 to 252-n set before a phrase constituting the sentence. The waiting time information 252-1 to 252-n may be arranged in accordance with the reproduction order of the waiting time (index n matches the reproduction order of phrases).

  By arranging the phrase specifying information 254-1 to 254-n and the waiting time information 252-1 to 252-n in accordance with the reproduction order, it is possible to function as sequence information regarding the reproduction order of the phrases.

  FIG. 4A is a diagram for explaining a generation process of memory write information (ROM image), and FIG. 4B is a diagram for explaining a usage form of the memory write information (ROM image).

  Reference numeral 100 denotes a voice editing tool (program or system) according to the present embodiment. Reference numeral 10 denotes an IC which is incorporated in an electronic device or the like and has a voice function for outputting a message preset as a user interface. The voice synthesis IC 10 plays back and outputs voice corresponding to the sentence based on the ROM image 152 and the sentence voice playback command 154 stored in the built-in ROM 20.

  Using the voice editing tool 100, a ROM image (a set of phrases voice data) stored in the built-in ROM of the voice synthesis IC 10 and a sentence playback command can be generated.

  The voice editing tool 100 can be operated as a voice editing system by installing the voice editing program of the present embodiment on a personal computer (PC), for example.

  The user can use the voice editing tool 100 to edit a voice guide message (sentence) that the voice synthesis IC 10 wants to utter. The ROM image 152 which is a set of phrases voice data files necessary for voice synthesis of the edited voice guide message and the voice data file of the ROM image are read out and voice synthesis of the voice guide message (sentence) is performed. A sentence speech synthesis command 154 can be created.

  The voice editing tool 100 may display a sheet screen as shown in FIGS. 6 to 25 on the display unit of the PC at the time of editing, and may receive input of the edit input information 162 from a PC keyboard or the like. Based on the edit input information 162 and phrase data (audio data, audio log information) 200 stored in the storage unit of the PC, sentence editing processing is performed, and a ROM image (memory writing to be written to the audio data memory) is performed based on the editing result. (Information) 152 and sentence voice reproduction command 154 may be generated and output.

  The sentence voice reproduction command 154 may have a configuration in which file specification information (for example, a file name) of phrases constituting a sentence is arranged in reproduction order, for example.

  The created ROM image 152 may be stored in a ROM that is a built-in memory of the speech synthesis IC 10 mounted on an electronic device such as an electronic device. The voice synthesis IC 10 includes a built-in ROM (non-volatile storage unit) 20 in which a ROM image (memory writing information) 152 generated by the voice editing tool 100 is stored, and receives and receives sentence information or a sentence voice reproduction command 154. It functions as a voice synthesizer that reads voice data from the built-in ROM (non-volatile storage unit) 20 based on sentence information or sentence voice playback command 154 and plays back and outputs a voice guide message corresponding to the sentence. The audio reproduction command 154 may be received from a host computer (for example, a main control unit such as an electronic device).

  The speech data of the phrase data 200 may be speech data generated by a TTS method that synthesizes speech from text data that is a collection of character data. The audio data may be held in a compressed format.

  The TTS tool 30 generates speech data corresponding to the phrase based on the text information 40 of the phrase to be created and the speech synthesis dictionary 50 for TTS.

  The TTS tool 30 is a TTS (text-to-speech) speech synthesis system that synthesizes speech from text data 40 based on the TTS speech synthesis dictionary 50. The TTS system has a parametric method that models the speech process of the human body and synthesizes sound, and has phoneme data consisting of voice data of a real person. If necessary, combine them and transform part of the connection part. There are many methods, such as the concati-native method for synthesizing and synthesizing the speech, and the corpus-based method for forming synthesized speech from real voice data by assembling speech from language-based analysis into speech. Is possible. For example, in the case of a concati native method or a corpus-based method, a phoneme dictionary may be provided, and the speech synthesis unit may generate speech data of synthesized speech corresponding to reading notation based on the phoneme dictionary.

  The TTS speech synthesis dictionary 50 includes, for example, a vocabulary dictionary and a phoneme dictionary. The vocabulary dictionary is a data dictionary in which reading notation corresponding to text notation is stored, and the phoneme dictionary is a dictionary that covers many cases effective for improving voice quality. The vocabulary dictionary is a dictionary for performing front-end processing in text-to-speech processing, and may be a dictionary that stores a symbolic linguistic representation corresponding to text notation (for example, reading data corresponding to text notation). . In front-end processing, the numbers and abbreviations in the text are converted into expressions for reading (called text normalization, preprocessing, tokenization, etc.), and each word is converted into a phonetic symbol, Processing to divide into prosodic units such as idioms, clauses, sentences, etc. (processing to assign phonetic symbols to words is text-to-phoneme (TTP) conversion or grapheme-to-phoneme (GTP) conversion) The symbolic language expression may be created and output by combining phonetic symbols and prosodic information. In the text normalization step, conversion processing may be performed so that synonyms, numbers, abbreviations, etc. included in the text can be uttered.

  The phoneme dictionary is a dictionary that stores waveform information of an actual sound (phoneme) corresponding to a symbolic language expression that is output from the front end. The main technologies for generating speech waveforms at the back end include concatenative synthesis and formant synthesis. Linked synthesis is basically a method of combining recorded audio fragments.

  The TTS tool 30 performs front-end processing and back-end processing based on the vocabulary information and sound information stored in the TTS speech synthesis dictionary 50, and speech data (phrase data) corresponding to the input phrase text information 40. 210 audio data) may be generated.

  FIGS. 26 and 27A to 27C are diagrams for explaining each process performed by the voice editing tool according to the present embodiment.

  In this embodiment, phrase data reading processing (P1) for reading phrase data 200-1, 200-2, 210-3,... From the phrase data storage unit 172 may be performed. The phrase data includes an audio data file corresponding to each phrase (a compressed audio file may be used. For example, an audio data file in an EOV format, an ADPCM format, or an AAC-LC format). The phrase data may include text data for reading the phrase sound and accompanying data associated with the sound data file such as the reproduction time of the phrase sound.

  In the present embodiment, a phrase list generation process (P2) for generating a phrase list 602 based on phrase data or phrase editing information may be performed. A phrase list is a collection of data having a data structure for managing data in units of phrases, and phrase data (audio data file or audio reading data) associated with an identification ID or index for specifying each phrase. Edit data (delay data, count value, etc.) related to phrase data and playback time data and size data). A phrase list sheet (an image displaying the phrase list in a tabular form) may be generated based on the phrase list and output to the display unit.

  In the present embodiment, an edit screen display process (P5) for displaying an edit screen for editing a sentence may be performed. A sentence list sheet may be displayed as an editing screen (sentence list sheet screen), the sentence playback time and file size may be displayed, and the sentence may be edited while viewing the display contents.

  In the present embodiment, sentence division processing (P3) may be performed in which sentence text input is divided into accepted phrases. For example, a sentence text input may be received from the sentence column of the sentence sheet screen, and the input sentence text may be divided into phrases.

  FIGS. 6A to 6C are diagrams schematically showing successful examples and failed examples of phrase list creation and phrase division processing.

For example, as shown in FIG. 27A, the phrase data “AAA” 200-1, “BBB” 200-2, and “CCC” 200-3 are read, and the phrase list 602 is generated based on these. In this case, as shown in FIG. 27B, when the sentence “AAACCC” is input, the sentence is divided into two phrases stored in the phrase lists “AAA” and “BBB”. The division processing is processing for comparing text data constituting the sentence with text corresponding to the phrase and data, and dividing the text data constituting the sentence into text data corresponding to the phrase. The text data constituting the sentence is a first text part, a second text part,. When divided into the nth text part, the first text part, the second text part,... The division process may be successful when all of the nth text part matches the text data of the phrase registered in the phrase list.
The sentence division result may be displayed on the sentence list sheet.

  For example, as shown in FIG. 27C, when the sentence “AAACBC” is input, the phrase data “CBC” is not registered in the sentence list 602, so that the sentence cannot be divided into phrases. In such a case, the sentence division result may not be displayed on the sentence list sheet, or a warning may be displayed that the sentence cannot be divided. In this way, even if there is an error in the sentence and it could not be divided into phrases, it can be immediately confirmed by the display, so it can be corrected immediately.

  Moreover, in this Embodiment, you may perform the phrase coupling | bonding process (P4) which produces | generates a sentence based on the designated phrase. For example, when the phrase data “AAA” and “BBB” are selected in this order, the phrase data “AAABBBB” may be generated by connecting the phrase data “AAA” and “BBB”.

  Further, in the present embodiment, the generation evaluation process (P6) may be performed in which the generated sentence or phrase is reproduced and the reproduction evaluation is performed. In the generation evaluation process (P6), the voice data corresponding to the phrase constituting the sentence is read from the phrase data storage unit based on the specific information of the phrase constituting the sentence, and the voice of the voice data read according to the sequence information of the sentence information is read. Processing for reproduction output may be performed. Further, based on the waiting time information of the sentence information, a silent section may be set before the phrase or between the phrases, and the voice data may be reproduced and output.

  Moreover, in this Embodiment, the delay time may be set before a phrase or between phrases, and the phrase space | interval adjustment process (P7) which adjusts a phrase space | interval may be performed. As the phrase interval adjustment process (P7), an edit input related to the waiting time information regarding the length of the silent section set for at least one of the phrases constituting the sentence and between the phrases is accepted, and the sentence information including the waiting time information is received. Generation may be performed.

  In the present embodiment, ROM image generation processing (P9) for generating a ROM image (contents of data stored in the ROM) when storing voice data necessary for speaking the created sentence in the memory is performed. Also good. In the ROM image generation process (P9), a storage target phrase to be stored in the voice data memory is extracted based on the phrase editing information, and the voice data of the extracted phrase is read from the phrase data storage unit and written to the voice data memory. Information (ROM image) may be generated. In this way, memory writing information (ROM image) can be generated so that the same audio data is not written redundantly for phrases used in a plurality of sentences.

  In this embodiment, sentence voice reproduction command generation processing (P9) for generating voice data to be read from the ROM image and a sentence voice reproduction command for instructing the reproduction order in order to synthesize sentence voice may be performed. In the sentence voice reproduction command generation process (P9), the voice data corresponding to the phrase constituting the sentence is read from the memory writing information (ROM image) stored in the voice data memory based on the phrase specifying information of the sentence information, and the sentence information is read. A sentence voice reproduction command for giving an instruction to reproduce and output the voice of the voice data read in accordance with the sequence information may be generated.

2. Specific Example of Implementation Using Spreadsheet Software FIGS. 5 to 25 are diagrams for explaining an example of realizing this tool using spreadsheet application software.

  This tool can also be realized using the macro function of general-purpose spreadsheet software.

  In this tool, voice data created by a voice creation tool in a TTS system or the like is handled as a phrase, and a sentence that becomes a voice guide message is edited by connecting phrases. As the audio data, an EOV format, an ADPCM format, an AAC-LC format, or the like may be used.

  Each function of this tool will be described. The screen of this tool is composed of a dialog screen as shown in FIG. 5 and a tabular sheet screen as shown in FIGS.

  By selecting radio buttons of the sentence list 412, the phrase list 414, and the parameter 416 in the sheet selection unit 410 of the dialog screen 400, the display of the sheets of the sentence list 412, the phrase list 414, and the parameter 416 can be switched.

  When the update button 422 of the phrase list 420 is selected, audio data necessary for editing is read from a folder containing audio data into a phrase list sheet, and a phrase list is created.

  When the phrase split button 432 of the tool 430 is selected, the sentences entered in the sentence field of the sentence sheet are selected and arranged from the phrases in the phrase list, and the phrases are configured to create a sentence.

  When the sentence update button 454 is selected, the sentences in the phrase column are matched with the phrases in the phrase list, and the matching sentences are arranged in the sentence column to form a sentence.

  When the play button 436 of the tool 430 is selected, the contents of the phrase are reproduced from the sentence column.

  When the light-out button 442 of the sentence list ROM 440 is selected, a sequence file (a file in which sentence generation information is stored or a file in which a sentence sound reproduction command is stored) and a ROM image are generated from the sentence. A sequence file is stored for all sentences on the sheet.

  When a ROM image is generated, phrases used in the sentence are automatically included in the ROM image, but even phrases that are not used in the sentence can be included in the ROM image by designation.

  Also, by selecting the light-out button 442, a sequence file of a sentence list is created, and then the total value of the data size is displayed in the total size column 444. If it exceeds the size specified by the parameter ROM image size, it is displayed in red. In this embodiment, even if the same phrase is used for a plurality of sentences, only one phrase data size is added. This value may be retained and displayed at the next startup.

  Also, by selecting the light-out button 442, a sentence list sequence file is created, and the total sentence playback time is displayed in the total time field 446.

  In the present embodiment, a sentence list sheet, a phrase list sheet, and a parameter sheet are included.

  FIG. 6 is an example of a sentence list sheet (display image). In the present embodiment, for example, the sentence list sheet 500 may be displayed on the display unit of a personal computer. Then, sentence information and phrase editing information may be generated (created or updated) based on the result of editing the sentence on the sentence list sort screen.

  The index column 510 is index information for accessing a sentence.

  The ID column 520 is an ID that serves as sentence identification information. When creating a sequence file, a file name may be generated with this ID.

  The sentence column 530 is a content of a sentence to be reproduced. It is also possible to create a sentence by arranging phrases, and it is also possible to directly input a sentence using a keyboard or the like. The size column 540 displays the total data size of phrases and waiting times that constitute a sentence. The time column 550 displays the sentence playback time. The comment field 560 can be used as a comment field for a sentence. The waiting time column 570 is a column for setting a waiting time set before a phrase, and is provided corresponding to each phrase.

  The phrase column 580 is a column for displaying phrases constituting a sentence, and for example, a maximum of 64 phrases may be displayed. Since a waiting time column 570 is provided corresponding to each phrase, when n phrase columns are displayed, a waiting time column is provided for each phrase, so that n waiting time columns are displayed.

  FIG. 7 is an example of a phrase list sheet (display image). In the present embodiment, for example, phrase list sheet 600 may be displayed on the display unit of a personal computer. In this embodiment, the read voice data of the voice creation tool is managed as a phrase. The phrase list sheet 600 may be generated based on phrase data or phrase editing information, and may be updated according to the editing result.

  The index column 610 is index information for accessing a phrase. The ID column 620 is an ID serving as phrase identification information, and is used as a phrase management ID for the read audio data. In the phrase name column 630, the file name of the audio data read as a phrase is displayed. In the phrase column, text data representing the contents (for example, reading and display) of the audio data read as a phrase is displayed. The size column 650 displays the size of audio data read as a phrase. In the time column 660, the reproduction time (m unit) of the audio data read as a phrase is displayed. The number-of-uses column 670 displays how many times the sentence is used in the entire sentence in which the voice data read as a phrase is created. When a value is written in the ROM writing field 680, the phrase is included in the ROM image when the light-out button (442 in FIG. 5) is pressed. It should be noted that a value of 1 is automatically written for a phrase used in a sentence when a write-out is performed, and a blank is automatically entered for a phrase that is not used. If an arbitrary value other than 1 is previously written in this field, it may be included in the ROM image regardless of whether it is used or not used.

  FIG. 8 shows an example of a parameter sheet (display image). In the present embodiment, for example, the parameter sheet 700 may be displayed on a display unit of a personal computer. Here you can set parameters for this tool.

  The waiting time default value 710 is a default waiting time (unit: ms) set before a phrase or between phrases when a sentence is created. When a waiting time (570 in FIG. 6) is set in the sentence sheet, the value may be prioritized.

  The sequence file format 720 is a parameter for setting whether to output data to be in binary format or text format in sequence file generation. In the text format, a text file in which a waiting time value and a phrase audio file name are separated by commas may be output on each line.

  FIG. 28 is a flowchart for explaining the work procedure of this tool.

  First, voice data corresponding to a phrase is prepared (step S10). Collect audio data for phrase editing in a folder.

  Next, audio data corresponding to the phrase is read (step S20). When the update button (422 in FIG. 5) is selected on the update screen of this tool, a folder selection dialog is displayed. Select a folder containing audio data in the phrase and select the OK button to select the file selection dialog. May be closed and the display may be automatically switched to the phrase list sheet. Audio data corresponding to the phrase is read, and a phrase list is created on the phrase list sheet as shown in FIG.

  Next, a sentence to be uttered as a voice guide message is created on the sentence sheet screen (step S30). A sentence can be created by selecting a sentence list sheet from the dialog screen. There are two ways to create a sentence: enter the sentence directly and connect the imported phrases. When entering a sentence directly, enter the sentence you want to create in the sentence field of the sentence list. For example, as shown in FIG. 10, a document “Bath temperature is 41 degrees” is entered in the sentence column 550 of the sentence list 500.

  Phrases that make up the sentence you entered must be loaded as data in the phrase list. In this example, data of “bath” 804, “temperature is 806”, “is 41 degrees” 802 or less shown in FIG. 11 is used as a phrase constituting the sentence.

  When the phrase split button on the dialog screen is selected after the input, the sentence 810 input in the sentence column of the sentence list sheet 500 is expanded into a plurality of phrases. As a result, appropriate phrase data is selected from the phrases read in the phrase list sheet, and the selected phrase data is displayed in the phrase columns 812, 814, and 816 of the phrase list as shown in FIG.

  Note that 100 (ms) is set as a default value in the waiting time fields 811, 813, and 815 corresponding to the phrase fields 812, 814, and 816. This setting can be changed by inputting to the sentence list screen.

  To connect the imported phrases, enter the text in the phrase field of the sentence list. When finished, select the Create sentence button in the dialog. As an example, a phrase in which “41” in “the bath temperature is 41 degrees” is changed from “41” to “49” is created (see FIG. 13). In this example, a sentence variation is created by changing the voice of the following sentence “”.

In this example, the data shown in the phrase group 820 of the phrase list in FIG. 14 is used as a phrase constituting the sentence.

  First, the basic sentence is input to the sentence sheet. For example, as shown by 830 in FIG. 15, “the bath temperature is 401 degrees” is input. Although it can be read as “Yonhyaku 1” in terms of document, it is played as “Yonju 1” in terms of sound. In this way, it is possible to create a rich variety with a small data configuration.

  When the phrase split button in the dialog is selected, the input sentence is expanded into a phrase as indicated by 832. The expanded phrase 832 is selected and copied to generate a plurality of phrase groups 834. Then, as indicated by 836, the phrase “1 degree” is changed from “2 degrees” to “9 degrees”.

  Then, as shown in FIG. 16, when the sentence phrase field 840 to be created is selected and the sentence creation button in the dialog is selected, the result of combining phrases into the sentence field is entered as shown at 842. By selecting another phrase field and selecting a sentence creation button in the dialog, another sentence can be created as shown at 844 in FIG.

  If the sentence is not completed, the text in the sentence column will be grayed out as shown at 850 in FIG. 18, so create a phrase necessary for creation with the voice creation tool and add a phrase. Do.

  When you create a sentence, the phrase is ready, but it is not selected properly, and the sentence may be incomplete. In such a case, the following configuration may be adopted as an avoidance method.

  For example, a break may be specified in the sentence. When “401 degrees” is input as indicated by reference numeral 860 in FIG. 19, it may not be clear whether “Yonhyaku 1” or “Yonju 1” is read. In such a case, it can be specified as a delimiter by inserting a half-width space in the sentence. By explicitly inputting “401 degrees” as indicated by reference numeral 862 in FIG. 19, it is possible to read “40 times”.

  Moreover, you may make it use a different phrase of the same reading. Since the phrase used in the sentence is found from the top of the phrase list, if there are a plurality of phrases that are read in the same way as in 870 and 872 in FIG. In such a case, a part of the audio data file may be edited with a text editor. For example, a file in which the attached information of the audio file of the phrase to be selected is selected, opened with a text editor, and edited. As shown in FIGS. 21 (A) and 21 (B), the file in which the attached information of the audio file is stored contains three character strings (text display information 892, data size 894, playback time 896) separated by commas. ing. A symbol (“*” in this example) is added to the character string of the text display information 892.

  When the list of the phrase list sheet is updated again, the phrase column of the phrase list is updated to the changed content as indicated by 898 in FIG.

  Then, in the sentence list, when an added symbol is entered and input to the sentence and the sentence division button is selected, the voice whose text display information is changed is selected as a phrase as shown in FIG.

  In addition, when there are a plurality of phrases having the same part, if a phrase used in the sentence is found from the top of the phrase list, a desired one may not be automatically selected. When there are phrases with the same part overlapping in this way, an appropriate phrase may be selected by clarifying the phrase delimiters on the sentence. For example, as shown in FIG. 24A, when there are a plurality of phrases including “power on” (see 902 and 904), when “turn off the bath power” is input as shown in 906, “power supply” of 904 May be selected as a phrase. In such a case, as indicated by reference numeral 908 in FIG. 24B, a half-width space 910 may be inserted as a delimiter symbol at the delimiter in the sentence column of the sentence list. In this example, a half-width space 910 is inserted behind the “power supply”. When the phrase division button is selected in this way, the phrase corresponding to the break can be selected.

  Next, the sentence is adjusted on the sentence sheet screen (step S40).

  After creating a sentence, you can adjust the interval between phrases. By inputting the time in ms unit in each delay time column of the created sentence, the length of the silent section set before the phrase can be set. The sentence adjustment result can be confirmed by sound by selecting the playback button in the dialog to utter the sentence.

  Next, the generated sentence sequence file (for example, a sentence voice reproduction command) and a ROM image are generated (step S50). When the light-out button on the dialog screen is selected, a sequence file (for example, a sentence sound reproduction command) or a ROM image can be generated. The total of the generated file sizes is displayed in the size total column (444 in FIG. 5).

When generating a ROM image, a phrase in which the ROM writing column 680 of the phrase list is not blank is stored in the ROM image.
In this example, “O” is entered in the 10th and 11th columns of the ROM write column 680 (see 912 and 914), and the ROM image is stored in the ROM image regardless of the presence / absence of the count value in the use count column 670. be able to.

  In this tool, the audio files of phrases written in the ROM based on the phrase list information are totaled to obtain a total value, and a reference value of the ROM size is determined based on the total value. The total value itself may be determined as the reference value for the ROM size, or the correspondence between the total value and the reference value for the ROMU may be determined, and the size reference value may be determined based on the correspondence.

  This tool also uses the sentence list information, the phrase information that constitutes the sentence, and the waiting time information corresponding to the phrase that constitutes the sentence, and the voice playback time of the sentence (if there are multiple sentences, the voice playback time of multiple sentences And the total audio playback time is displayed in the total time column 446 of the dialog.

  According to the present embodiment, the phrase used to compose the sentence that is the voice guidance message is automatically selected, so there is no human error such as forgetting to put it in, but it was intentionally not used in the sentence. Phrases you want to include can also be included, so there is a high degree of freedom.

  Moreover, since the file length and pronunciation time are managed, the size when ROMized is known. Also, it is convenient because you can insert a waiting time between phrases, and you can utter and check on the spot.

  Further, since necessary audio files are automatically output as a ROM image, work efficiency can be improved and human error can be included.

  In addition, for example, a sentence including a variation can be efficiently created only by changing a part of the sentence.

  In addition, since it is possible to know the memory size necessary for reproducing a necessary sentence, it becomes easy to adjust the cost balance such as narrowing down or adding an audio file to be stored.

  By adjusting the waiting time (delay) between phrases, the nuance of utterance can be controlled easily.

  In addition, this invention is not limited to this embodiment, A various deformation | transformation implementation is possible within the range of the summary of this invention.

  The present invention includes configurations that are substantially the same as the configurations described in the embodiments (for example, configurations that have the same functions, methods, and results, or configurations that have the same objects and effects). In addition, the invention includes a configuration in which a non-essential part of the configuration described in the embodiment is replaced. In addition, the present invention includes a configuration that exhibits the same operational effects as the configuration described in the embodiment or a configuration that can achieve the same object. Further, the invention includes a configuration in which a known technique is added to the configuration described in the embodiment.

An example of a functional block diagram of the voice editing system of the present embodiment. The figure for demonstrating phrase data and phrase edit information. It is a figure for demonstrating sentence information. FIG. 4A is a diagram for explaining a process of generating memory write information (ROM image). FIG. 4B is a diagram for explaining how to use the memory writing information (ROM image). Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software Example of realizing this tool using spreadsheet application software The figure for demonstrating each process performed with the audio | voice editing tool of this Embodiment. 27A to 27C are diagrams for explaining each process performed by the voice editing tool according to the present embodiment. The flowchart for demonstrating the work procedure by this tool.

Explanation of symbols

1 speech synthesis IC, 20 built-in ROM, 30 TTS tool, 50 TTS speech synthesis dictionary, 100 speech editing tool (program, system), 110 processing unit, 120 sentence editing processing unit, 122 sentence information refining processing unit, 124 phrase editing Information refining unit, 130 Memory write information (ROM image) generation unit, 132 sentence voice playback command generation unit, 140 sentence voice playback output processing unit, 150 Non-volatile storage unit, 152 Memory write information, 154 sentence voice playback command, 160 operation , 170 storage unit, 172 phrase data storage unit, 174 sentence information storage unit, 176 phrase edit information storage unit, 180 information "storage medium, 190 display unit, 192 sound output unit, 196 communication unit

Claims (16)

A program that allows a computer to function as a voice editing tool,
A phrase data storage unit storing phrase data including phrase voice data and phrase text data;
A sentence editing processing unit that performs sentence editing processing based on the phrase data;
Based on the sentence editing process result, the sentence function generation processing unit for generating sentence information including phrase specifying information for specifying a phrase constituting the sentence and sequence information regarding the reproduction order of the phrases, and causing the computer to function,
The sentence editing processing unit
The sentence text data is received, and based on the phrase text data, sentence split processing is performed to divide the received sentence text data into a plurality of phrases,
The sentence information generation processing unit
A program for generating sentence information including phrase specifying information and sequence information of a phrase constituting a divided sentence. In claim 1,
A program comprising: a phrase editing information generation processing unit that generates editing information of a phrase constituting the sentence based on a sentence editing process result, and stores the generated phrase editing information in association with the phrase data. In claim 2,
The phrase editing information generation processing unit
A program characterized by counting the number of times a phrase used in a plurality of sentences or a phrase used a plurality of times in one sentence and holding the count value as phrase editing information. In any one of Claims 2 thru | or 3.
Memory writing information for extracting a storage target phrase to be stored in the audio data memory based on the phrase editing information, reading out the audio data of the extracted phrase from the phrase data storage unit, and writing to the audio data memory based on the read audio data Including a memory write information generation unit for generating
A program for generating memory write information so that the same audio data is not written twice for phrases used in a plurality of sentences. In claim 4,
The memory write information generation unit
A program for calculating a total size of the memory write information and outputting size information based on the calculation result. In any one of Claims 1 thru | or 5,
The sentence editing processing unit
Accepts phrase selection input stored in the phrase data storage unit, performs phrase combination processing to create a sentence based on the selected phrase,
The sentence information generation processing unit
A program for generating sentence information including phrase specifying information and sequence information of a phrase constituting a created sentence. In any one of Claims 1 thru | or 6.
The sentence editing processing unit
A program for performing a display output process for displaying phrases constituting a sentence based on a phrase division process result. In any one of Claims 1 thru | or 7,
The text data of the sentence includes delimiter data indicating phrase delimiters,
The sentence editing processing unit
A program for performing the sentence division processing based on the delimiter data. In any one of Claims 1 thru | or 8.
Sentence voice playback output processing for reading out voice data corresponding to a phrase constituting the sentence from the phrase data storage unit based on specific information of the phrase constituting the sentence and reproducing and outputting the voice data read according to the sequence information of the sentence information A program characterized by including a part. In any one of Claims 1 thru | or 9,
The sentence editing processing unit
Edit input related to waiting time information related to the length of the silent section set for at least one of the phrases constituting the sentence and between the phrases,
The sentence information generation processing unit
A program for generating sentence information including the waiting time information. In claim 10,
The sentence audio reproduction output processing unit
A program that reproduces and outputs the sound of sound data by setting a silent section before a phrase or between phrases based on waiting time information of sentence information. In any of claims 10 to 11,
The sentence editing processing unit
A sentence edit screen display control unit for controlling display of a sentence edit screen for editing a sentence;
The sentence edit screen display control unit
The sentence and the phrase constituting the sentence are displayed in a tabular form, and each column includes a sentence display field, a phrase display field constituting the sentence, and a silence interval setting field provided between phrases or in front of the phrase. The section setting field is provided between the phrase display field and the phrase display field. In any one of Claims 1 to 12,
A sentence voice playback command generation processing unit for generating a sentence voice playback command for instructing playback of voice data necessary for playback of sentence voice from the voice data memory in an order corresponding to the read sentence based on the sentence information; A program characterized by that. An audio editing system,
A phrase data storage unit storing phrase data including phrase voice data and phrase text data;
A sentence editing processing unit that performs sentence editing processing based on the phrase data;
A sentence information generation processing unit for generating sentence information including phrase specifying information for specifying phrases constituting the sentence and sequence information related to the reproduction order of the phrases based on a sentence editing process result;
The sentence editing processing unit
The sentence text data is received, and based on the phrase text data, sentence split processing is performed to divide the received sentence text data into a plurality of phrases,
The sentence information generation processing unit
A speech editing system characterized by generating sentence information including phrase specifying information and sequence information of a phrase constituting a divided sentence. A method of manufacturing a semiconductor integrated circuit device for speech synthesis, including a non-volatile storage unit,
Storing phrase data including phrase voice data and phrase text data in a phrase data storage unit;
A sentence editing processing unit step for performing sentence editing processing based on the phrase data;
Sentence information generation processing step for generating sentence information including phrase specifying information for specifying phrases constituting the sentence and sequence information regarding the playback order of phrases based on the sentence editing processing result, and voice based on the phrase editing information A memory write information generation step of extracting a storage target phrase to be stored in the data memory, reading out the voice data of the extracted phrase from the phrase data storage unit, and generating memory write information to be written in the voice data memory;
Writing the memory write information to be written into the nonvolatile storage unit,
Including
In the sentence editing process step,
The sentence text data is received, and based on the phrase text data, sentence split processing is performed to divide the received sentence text data into a plurality of phrases,
In the sentence information generation processing step,
Generate sentence information including the phrase identification information and sequence information of the phrases that make up the divided sentence,
A method of manufacturing a semiconductor integrated circuit device, wherein memory write information is generated so that the same audio data is not written redundantly for a phrase used in a plurality of sentences. A non-volatile storage unit in which memory write information generated by the voice editing program according to claim 4 is stored;
A voice synthesizer that receives sentence information or a sentence voice reproduction command, reads out voice data from the nonvolatile storage unit based on the received sentence information or sentence voice reproduction command, and reproduces and outputs a voice guide message corresponding to the sentence;
A semiconductor integrated circuit device.