JP3999078B2 - Voice data distribution device and client terminal - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an audio data distribution apparatus and a distribution requester terminal that distribute audio data to a user terminal via a data network such as the Internet.
[0002]
[Prior art]
When reading a long text of an e-mail or a web page on the screen, there is a need to present the text as a voice to reduce the burden on the eyes. In response to this need, a method for realizing voice presentation using a voice data distribution apparatus is known. In such an audio data distribution apparatus, in order to convert document data in a text format or the like into audio data, special software called a speech synthesis engine is required. Therefore, the conversion to the audio data is used for distributing audio data. An audio data distribution system that services users in advance is also known. In this regard, Japanese Patent Laid-Open No. 2001-282268 discloses a homepage viewer or a telephone by receiving text data such as a weather forecast from a requester, creating speech synthesis data and distributing it to a Web server or a telephone server as a distribution source. An audio data distribution system that enables a user to listen to information such as weather forecasts by voice is disclosed. With this configuration, a distribution requester who wants to distribute audio data can transmit the audio data by simply transmitting document data in a text format or the like to the data distribution system, even if his / her device does not have a speech synthesis function. It is said that it can be provided to users at the delivery destination.
[0003]
By the way, on the premise that Japanese is the target language, speech data is usually synthesized from text data, which is a kana-kana mixed sentence, using speech dictionary data, word dictionary data, prosodic rule data, and speech segment data. Is generated.
[0004]
[Problems to be solved by the invention]
The voice data generated in this way is always distributed with the occurrence of an error in reading or the occurrence of an unknown word, that is, the corresponding voice cannot be determined because it is not registered in the word dictionary, and the reading is not yet determined. The occurrence of danger is expected. In particular, in Japanese, there are problems such as the occurrence of many unknown words due to different readings or technical terms due to differences in the fields to which the content of the text belongs, such as economic, cultural, political, and entertainment fields. is expected. Therefore, as a result, there is a risk that the user who listens to the voice data including the wrong reading and listens to the voice data may misunderstand the information. Providing such erroneous voice data has been a factor that impairs the reliability of the voice data distribution service and hinders its spread.
[0005]
The present invention has been made in view of the above problems, and an object thereof is to provide a reliable audio data distribution apparatus.
[0006]
[Means for Solving the Problems]
An audio data distribution apparatus according to the present invention is an audio data distribution apparatus that distributes audio data via a data network, receives at least one series of text data from at least one client terminal, and converts the text data by voice synthesis. In response to a correction request from the client terminal, voice data storage means for converting into a series of voice data and storing it for distribution, The voice data corresponding to the correction request is subjected to voice synthesis again according to the content of the correction request to obtain corrected voice data, and the obtained corrected voice data is transmitted to the client terminal. The corrected voice data stored in the voice data storage means in the corrected voice data corresponding to the delivery approval message in response to the delivery approval message from the corrected voice data transmitting means and the requester terminal. Voice data updating means for updating It is characterized by including.
[0007]
The distribution request terminal according to the present invention is: Claim 1 Audio data distribution device Very small It is a client terminal that requests distribution of at least one series of audio data, A distribution request information display means for displaying audio data distribution request information for prompting input of text data to be converted into the audio data; and a reproduction instruction or an approval instruction for the corrected audio data while prompting input of contents of the correction request Correction request information display means for displaying voice data correction request information prompting input; It is characterized by including.
[0008]
DETAILED DESCRIPTION OF THE INVENTION
Embodiments of the present invention will be described in detail with reference to the accompanying drawings.
<First embodiment>
FIG. 1 is a first embodiment of the present invention, and shows the overall system configuration including an audio data distribution apparatus. The audio data distribution device (also referred to as an audio data distribution system) includes an audio data distribution server 10 and an audio data synthesis server 20.
[0009]
Referring to the voice data synthesis server 20 shown on the right side of FIG. 1, the voice data synthesis server 20 is connected to the Internet 30 and enables communication with the client terminal 40 and / or the user terminal 100. The hardware configuration of the voice data synthesis server 20 is configured as a normal server computer. As shown, the software configuration of the voice data synthesis server 20 includes a control program 22, a TCP / IP unit 23, an HTTP / CGI unit 24, a voice synthesis processing unit 25, a voice data accumulation request unit 26, including. The control program 22 is an operating system that controls the basic control of the entire voice data synthesis server 20. The TCP / IP unit 23 executes a TCP / IP protocol procedure under the control of the control program 22 and realizes data communication with the client terminal 40 and / or the user terminal 100 via the Internet 30. The HTTP / CGI unit 24 distributes a web page for accepting a voice data distribution request to the Internet 30 via the TCP / IP unit 23 and receives text data from the requester terminal 40 by the CGI function. It has a function. The HTTP / CGI unit 24 also has a function of returning voice-synthesized voice data to the client terminal 40 and receiving a correction instruction. The HTTP / CGI unit 24 realizes data communication based on HTTP (HyperText Transfar Protocol; see IETF: RFC2616).
[0010]
The speech synthesis processing unit 25 has a function of converting text data input from the HTTP / CGI unit 24 into speech data. The format of the input text data is usually composed of plain text, that is, a JIS kanji character code string, but may be other document formats. The output voice data is composed of phoneme data corresponding to the voice waveform, and is usually collected into one file. This file may be any audio waveform format file that can be reproduced by the user terminal 100 and / or the client terminal 40, and various file formats such as WAV files and MP3 files are assumed. The speech synthesis processing unit 25 includes, for example, a word dictionary data file 251 in which information on notation, reading, accent, and part of speech of about 100,000 words is stored in association with each word, and control rule data on basic frequency and sound pressure. The stored prosodic rule data file 252 is connected to the speech segment data file 253 storing waveform data for each phoneme. The speech synthesis processing procedure of the speech synthesis processing unit 25 first generates an intermediate language that is an accented kana character string by using text data that is a kana-kana mixed sentence and word dictionary data of the word dictionary data file 251. Next, from the generated intermediate language, using the prosodic rule data in the prosodic rule data file 252, a synthesis parameter including a speech unit number, pitch pattern information, phonological duration information, and the like is generated. Then, in accordance with the generated synthesis parameter, the speech unit data of the speech unit data 253 is read out and sequentially connected to generate speech waveform data. Thereby, the speech waveform information of the speech data is generated as, for example, PCM data with a sampling frequency of 8 kHz and quantization of 16 bits, and is temporarily stored as speech data 63 in an appropriate primary storage device of the speech data synthesis server 20. .
[0011]
The speech synthesis processing unit 25 further has a function of returning an unknown word as a character string. Here, the unknown word is a word that is not registered in the word dictionary data file and may be misread. The speech synthesis processing unit 25 converts a word determined to be an unknown word into a sound with a predetermined appropriate reading, and outputs a list of words determined to be an unknown word as an unknown word list 64. The unknown word list 64 is temporarily stored in the appropriate primary storage device of the voice data synthesis server 20 together with the previous voice data 63.
[0012]
The voice data accumulation requesting unit 26 transmits the voice data 63 temporarily stored to the voice data delivery server 10 in response to the delivery approval OK message for the voice data from the client terminal 40 and accumulates it therein. At least, it has a function of requesting delivery to each user terminal 100 toward the Internet 30.
Referring to the audio data distribution server 10 shown on the left side of FIG. 1, the audio data distribution server 10 is connected to the Internet 30 and enables data communication with the user terminal 100 and / or the client terminal 40. . The hardware configuration of the audio data distribution server 10 is configured as a normal server computer. As shown in the figure, the software configuration of the voice data synthesis server 20 includes a control program 12, a TCP / IP unit 13, an HTTP unit 14, a voice data storage unit 15, and a voice data database 60 (for distribution). Hereinafter, it is referred to as a voice data DB).
[0013]
The control program 12 is an operating system that governs basic control of the entire voice data distribution server device 10. The TCP / IP unit 13 executes a TCP / IP protocol procedure under the control of the control program 12 and realizes data communication with the client terminal 40 and / or the user terminal 100 via the Internet 30. The HTTP unit 14 has a function of distributing desired audio data via the TCP / IP unit 13 to the user terminal 100 or the requester terminal 40 that requests distribution of the audio data stored in the audio data DB 60. Have. The audio data DB 60 includes an identifier group including a plurality of identifiers, and an audio data group including a plurality of audio data associated with each of the identifiers. The configuration of the audio data DB 60 can be realized by a normal file system having an identifier as a file name.
[0014]
FIG. 2 shows an internal configuration of the client terminal 40 shown in FIG. Here, the client terminal 40 is connected to the Internet 30 to enable data communication. The hardware configuration of the client terminal 40 is a normal network client terminal such as a personal computer, to which a normal display 51 and a keyboard 54 are connected. The hardware configuration of the client terminal 40 further includes a speaker 52 for reproducing and verifying audio data and a microphone 53 for directly generating audio data by voice input by the operator. The software configuration of the client terminal 40 includes a control program 41 that controls the entire basic control of the client terminal 40, a TCP / IP unit 42 for realizing data communication via the Internet 30, and an I including a keyboard 54. An I / O control unit 43 that realizes input / output of the / O device in cooperation with the control program 41, a voice input unit 46 that digitally captures voice input from the microphone 53, and a TCP / IP unit 42 A web browser unit 44 that displays a web page received via the web browser and transmits the operator's input to the internet again to the Internet, and audio data captured via the web page displayed on the web browser unit 44 And an audio data reproduction unit 45 for reproduction through 52.
[0015]
The requester terminal 40 uses the microphone 53 and the voice input unit 46 to directly input the voice data of the operator in conjunction with the text input field displayed on the Web browser unit 44 when the text data is corrected. It can also be generated directly.
FIG. 3 shows an example of an audio data distribution request screen on the client terminal 40. The voice data distribution request screen 80 includes a text data input field 81, a voice data conversion instruction button 82, and a voice synthesis processing condition setting field 83. The text data input field 81 is a field in which the operator of the client terminal 40 inputs characters as text data for a document that is actually desired to be distributed as voice data. When the voice data conversion instruction button 82 is instructed after the text data is input, the text data is transmitted to the voice data synthesis server 20. The voice synthesis processing condition setting field 83 enables setting of detailed processing conditions when the voice data synthesis server 20 executes voice synthesis processing. In the example of this figure, the example which enables the voice quality setting of voice data, the speed setting, and the setting of unknown word display is shown. The processing conditions that can be set in the speech synthesis processing condition setting field 83 include various settings such as setting the encoding speed (16 kbps, 32 kbps, etc.) of other generated speech data and the field of the word dictionary. .
[0016]
FIG. 4 shows an example of a voice data correction request screen on the client terminal 40. The voice data correction request screen 84 displays a voice data playback button 85 for instructing playback of voice data using the speaker 52, a correction input field 86 for prompting character input as a correction instruction for text data, and an unknown word list. It includes an unknown word list field 87, a word information input field 88 that prompts the user to input word information as a correction instruction for the unknown word, and an OK message button 89 that approves delivery of the voice data or issues a correction instruction. The word information input field 88 further includes a reading input field 881 that prompts the user to input the reading, that is, “reading”, and a part of speech specification field 882 that specifies the part of speech as a correction instruction for the word selected on the unknown word list 87. And an accent designation field 883 that prompts designation of the accent information according to the reading designated in the reading input field. It should be noted that a form for providing a distribution approval button and a correction instruction button may be provided separately.
[0017]
FIG. 5 shows a processing procedure of the voice data synthesis server 20 and the requester terminal 40. The sequence shown in this figure will be described with reference to the components shown in FIGS. 1 and 2 as appropriate.
First, the voice data synthesis server 20 transmits a voice data distribution request screen to the requester terminal 40 by the HTTP / CGI unit 24 (step S11). This is transmitted when the client terminal 40 accesses the voice data distribution request screen by designating the address of the voice data synthesis server 20. In response to this transmission, the client terminal 40 receives and displays the voice data distribution request screen by the web browser unit 44 (step S12). Next, the input of text data is received from the operator of the client terminal 40 and transmitted to the voice data synthesis server (step S13). In response to this transmission, the voice data distribution server 20 receives the text data by the HTTP / CGI unit 24 (step S14).
[0018]
Next, the speech data synthesis server 20 performs speech synthesis processing on the received text data by the speech synthesis processing unit 25 (step S15). In this synthesizing process, the synthesizing process may be performed in accordance with detailed voice synthesizing process conditions specified on the voice data distribution request screen. The speech synthesis processing unit 25 creates speech data 63 and an unknown word list 64 as a result of the synthesis process. Next, the voice data synthesis server 20 transmits a voice data correction request screen including the obtained voice data 63 and the unknown word list 64 to the client terminal 40 by the HTTP / CGI unit 24 (step S16). In response to this transmission, the client terminal 40 receives and displays the voice data correction request screen by the web browser unit 44 (step S17). In response to the display of the voice data correction request screen, the operator of the client terminal 40 appropriately determines whether or not the synthesized voice data is appropriate, and edits the text data as necessary.
[0019]
To explain an example of this editing, the text data "I can't hear the words I'm talking about on this side." When the voice that can be heard is generated on this side, the operator of the client terminal 40 adds a punctuation to the original text data, and “the spoken word on this side is heard. By giving a correction instruction “No”, it is possible to request the speech synthesis process again and generate an appropriate speech. In addition, the text data “He has Yamato soul” is appropriate to read “He has Yamatoda Mashii” in the context, but if the voice that sounds “He has Daiwa da Mashii” is generated, the operator Can change the "Yamatotama" part of the original text data to "Yamatoda Mashii" and Kana, and generate a correct voice by instructing correction. In this case, even if the operator gives a correction instruction by inputting the word information of “Yamato soul” from the word information input field 88 shown in FIG. The word information input here is used together with the word dictionary data 251 when the speech synthesis processing unit 25 performs speech synthesis processing again.
[0020]
After the above editing operation, the client terminal 40 transmits a voice data correction instruction (correction request) or an OK message to the voice data synthesis server via the web browser unit 44 (step S18). The OK message without the correction instruction means that the operator of the client terminal 40 approves the actual distribution because the correction instruction is not necessary for the voice data.
[0021]
In response to this transmission, the voice data synthesis server 20 receives a correction instruction (correction request) or an OK message by the HTTP / CGI unit 24 (step S19). Next, it is determined whether or not it is a correction instruction / OK (step S20). If there is a correction instruction, the process returns to the speech synthesis process in step S15. On the other hand, if it is OK, the voice data synthesis server 20 causes the voice data distribution server 10 to store the voice data via the voice data storage request unit 26 (step S21). The voice data storage request unit 26 requests the voice data storage unit 15 of the voice data distribution server 10 to store voice data via the Internet 30, and the voice data storage unit 15 stores the voice data in the voice data DB 60. As a result, the accumulated audio data can be distributed to the user terminal 100 or the client terminal 40 via the Internet 30 by the HTTP unit 14 of the audio data distribution server 10.
[0022]
Next, the voice data synthesis server 20 notifies the requester terminal of a registration completion message through the HTTP / CGI unit 24 (step S22). In response to this transmission, the client terminal 40 receives a registration completion message by the Web browser unit 44 (step S23). This registration completion message is displayed to the operator on the client terminal 40.
[0023]
As described above, in the first embodiment, since the voice data distribution system is provided with the voice synthesis server, the requester of the voice data distribution does not need to have the task of providing the client terminal with the voice synthesis function. Thus, it is possible to make appropriate corrections and additions to the synthesized voice data.
In addition, although the delivery by HTTP server was demonstrated as a delivery form of audio | voice data, it is not restricted to this form, Other delivery forms, such as a file transfer v by FTP (File Transfer Protocol) and a delivery form by UDP (User Datagram Protocol) But it ’s okay.
<Second embodiment>
FIG. 7 shows another configuration of the voice data synthesis server 20 according to the second embodiment of the present invention. Here, the hardware configuration of the voice data synthesis server 20 is the same as that of the first embodiment, and the software configuration is partially added with functions. Only the function addition part will be described. Referring to FIG. 7, an identifier determination unit 27 and an audio / sound data information calculation unit 28 are provided.
[0024]
The identifier determining unit 27 has a function of automatically determining a unique identifier that can be accessed on the Internet 30 as a voice data file of voice data that is synthesized and distributed based on a distribution approval OK message from the client terminal. Have As an identifier format, a request source IP address (Internet Protocol; Source-address; IETF: RFC791) of an IP header can be used as information for specifying a URI (Uniform Resource Identifiyer; see IETF: RFC2396).
[0025]
As an example of the identifier automatic generation method of the identifier determination unit 27, there is a method including a counter memory. In this example, the identifier determination unit 27 includes a counter memory. As soon as automatic generation starts, the identifier determination unit 27 reads a value from the counter memory. Then, an identifier included as a character string of this value is generated and the value of the counter memory is incremented. The value in the counter memory is saved until the next identifier generation. Specifically, when the value read from the counter memory is 123, for example, an identifier is generated as http: //aaa.bbb.cccc.dddd/123.wav, and the counter is incremented immediately, so that the value 124 Prepare for the next identifier generation. Another example of the automatic generation method is a method using time information. In this example, the identifier determination unit 27 is provided with a clock that provides time information. As soon as automatic generation is started, the identifier determination unit 27 acquires time information from the clock and generates an identifier included as a character string of this value. Specifically, when the time information obtained from the clock is December 3, 2001 10: 29: 15: 33 ms, for example, the following is performed.
[0026]
http: //aaaa.bbbb.cccc.dddd/2001120310291533.wav
And an identifier. The identifier generation function by the identifier determination unit 27 may be realized so as to automatically generate an identifier from the contents of the target text data. As a method in this case, it is conceivable to pre-define the format of the text data and automatically extract a character example for which an identifier is scheduled from a character example of a predetermined field. As a result, the client can specify the desired identifier name himself. Since the client can manage the identification of the voice data on the Internet by the identifier name designated by the client, an easy-to-use system can be provided. The voice data accumulation request unit 26 of the voice data synthesis server 20 adds the identifier determined by the identifier determination unit 27 to the voice data 63 and requests the voice data distribution server 10 to store.
[0027]
The voice data information calculation unit 28 calculates voice data information based on the voice data synthesized by the voice synthesis processing unit 25. Here, the audio data information is the data size of the audio data and the reproduction time length of the audio data. The audio data information calculation unit 28 calculates the reproduction time of the audio data from the size of the input audio data and the predetermined audio data format. Specifically, assuming that the audio data size is N bytes, the format is a sampling frequency of 8 kHz, and a quantization of 16 bits, the playback time is calculated as N / (16) [ms].
[0028]
The voice data synthesis server 20 transmits the playback time calculated by the voice data information calculation unit 28 to the client terminal 40 together with the identifier output from the identifier determination unit 27 using the HTTP / CGI unit 24.
FIG. 7 shows an example of a voice data registration confirmation screen displayed on the client terminal 40. The audio data registration confirmation screen 90 includes an identifier display field 91 and a playback time display field 92. The identifier display field 91 displays the identifier determined by the identifier determination unit 27 of the voice data synthesis server 20. The reproduction time display field 92 displays the predicted reproduction time of the voice data calculated by the voice data information calculation unit 28 of the voice data synthesis server 20.
[0029]
In the second embodiment described above, the operator of the client terminal can recognize the identifier of the voice data as a result of the operation of the processing procedure similar to that of the first embodiment. For example, the Web page manager updates the identifier by embedding it as a hyperlink in the Web page to be managed, and registers it in the Web server. When a user of a Web page displays the updated Web page with a browser or the like and wants to output the sound, the user can obtain the sound output by using the added hyperlink. In the second embodiment, it is possible to recognize reproduction time information of audio data. As a result, it is possible to know the listening time and the amount of communication data when audio distribution is performed, and it is possible to assume a specific usage image for the user of the audio data, so that more sophisticated audio data distribution is possible. It becomes possible.
[0030]
In the first and second embodiments described above, a single client terminal or user terminal has been described for ease of explanation. However, the voice data distribution system according to the present invention has a large number of single clients. A terminal or a user terminal is assumed. Therefore, the audio data that can be handled by the audio data distribution system is not limited to the number shown in the figure, and can accommodate a large number of audio data.
[0031]
In addition, the audio data distribution apparatus in the first and second embodiments described above is composed of two servers, an audio data distribution server and an audio data synthesis server. This is because the system can be easily realized by adding a new voice configuration server to the operation mode in which only the server exists. However, a configuration in which these two servers are integrated into a server device as a single hardware is naturally possible.
[0032]
【The invention's effect】
As described above, according to the audio data distribution device and the distributor terminal according to the present invention, it is possible to confirm the reproduction of the audio data to be distributed and make appropriate corrections, thereby avoiding utterances due to erroneous reading. it can. Thereby, a reliable audio data distribution apparatus is provided.
[Brief description of the drawings]
FIG. 1 is a block diagram showing an overall configuration of an audio data distribution system according to a first embodiment of the present invention.
FIG. 2 is a block diagram showing a configuration of a client terminal shown in FIG.
FIG. 3 is a diagram showing an example of an audio data distribution request screen displayed on the requester terminal 40;
FIG. 4 is a diagram showing an example of a voice data correction request screen displayed on the client terminal 40.
FIG. 5 is a sequence diagram showing processing procedures of the voice data synthesis server 20 and the client terminal 40;
FIG. 6 is a block diagram showing another configuration of the voice data synthesis server 20 according to the second embodiment of the present invention.
7 is a diagram showing an example of a voice data registration confirmation screen displayed on the client terminal 40. FIG.
[Explanation of symbols]
10 Voice data distribution server
12, 22, 41 Control program
13, 23, 42 TCP / IP section
14 HTTP part
15 Audio data storage
20 Speech data synthesis server
24 HTTP / CGI Department
25 Speech synthesis processor
26 Voice data storage request section
27 Identifier determination unit
28 Voice data information calculator
30 Internet
40 Client terminal
43 I / O controller
44 Web browser
45 Audio data playback section
46 Voice input part
51 display
52 Speaker
53 Microphone
54 keyboard
60 voice data database
63 Voice data
64 Unknown word list
80 Voice data distribution request screen
84 Voice data correction request screen
90 Audio data registration confirmation screen
100 user terminal

Claims (7)

An audio data distribution apparatus for distributing audio data via a data network,
Voice data storage means for receiving at least one series of text data from at least one client terminal, converting the text data into a series of voice data by voice synthesis and storing the data for distribution;
In response to a correction request from the requester terminal, for voice data corresponding to the correction request, voice data correcting means for performing voice synthesis again according to the content of the correction request to obtain corrected voice data;
Corrected voice data transmitting means for transmitting the obtained corrected voice data to the client terminal;
Voice data update means for updating the voice data before correction stored by the voice data storage means to the corrected voice data corresponding to the delivery approval message in response to the delivery approval message from the requester terminal;
An audio data distribution apparatus comprising: The audio data correction transmission means, according to claim 1, wherein Rukoto to correct the Kion voice data before based on the modified request containing the word information for modifying information for modifying the target audio data and / or the unknown word Osamu Audio data distribution device. Before an identifier determining means for determining an identifier of the Kion voice data, further audio data distribution according to claim 1 or 2 characterized in that it comprises an identifier transmission means for transmitting to the requester terminal corresponding to the determined identifier apparatus. The identifier determination unit, before counter which is updated each Kion voice data, current time, or the audio data distribution apparatus according to claim 3, wherein the determining based on the information extracted from the text data. Before calculates a predicted play time of Kion voice data, the prediction reproduced audio data distribution apparatus time, characterized in that it further includes means for transmitting to the corresponding requester terminal according to claim 1, wherein. Even without least the audio data distribution apparatus according to claim 1, wherein a requester terminal for requesting the distribution of audio data of one series,
Distribution request information display means for displaying audio data distribution request information that prompts input of text data to be synthesized with the audio data;
Correction request information display means for prompting input of the content of the correction request and displaying voice data correction request information for prompting input of a reproduction command or approval command for the corrected voice data;
A distribution requester terminal characterized by including: 7. The distribution requester terminal according to claim 6, wherein the correction request information display means prompts input of a content of a correction request including correction information for correction target audio data and / or word information for an unknown word .

Images