Multiple language speech synthesizer

• US 6,243,681 B1
• Filed: 03/14/2000
• Issued: 06/05/2001
• Est. Priority Date: 04/19/1999
• Status: Expired due to Term

• Current Assignee: OKI Electric Industry Company Limited
• Original Assignee: OKI Electric Industry Company Limited
• Inventors: Ohtsuki, Koji, Guji, Yoshiki
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Nolan, Daniel A.
• Application Number:
  US09/525,057
• Time in Patent Office: 448 Days
• Field of Search: 704/2, 704/8, 704/277, 704/220, 704/260, 379/289, 379/290, 707/4, D14/158
• US Class Current: 704/260
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

In a speech synthesizer for converting text data to speech data, it is possible to realize high quality speech output even if the text data to be converted is in many languages. The speech synthesizer is provided with a plurality of speech synthesizers for converting text data to speech data and each speech synthesizer converts text data of a different language to speech data in that language. For conversion of particular text data to speech data, one of the plurality of speech synthesizers is selected and caused to carry out that conversion.

Claims

1. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein text data acquired by the data acquisition means is text data contained in electronic mail acquired from an electronic mail server.

2. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein text data acquired by the data acquisition means is text data contained in content acquired from a WWW server.

3. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein, based on an instruction provided using the telephone, the conversion control means selects one of the plurality of speech synthesizing means and causes conversion to speech data in the selected speech synthesizing means, and

wherein text data acquired by the data acquisition means is text data contained in electronic mail acquired from an electronic mail server.

4. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

buffer means for holding text data acquired by the data acquisition means;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech of synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein, based on an instruction provided using the telephone the conversion control means selects one of the plurality of speech synthesizing means and causes conversion to speech data in the selected speech synthesizing means,

wherein, if the conversion control means switches selection of the speech synthesizing means during conversion of particular text data, conversion to speech data of text data held in the buffer means is carried out in the speech synthesizing means newly selected as a result of the switch, and

wherein text data acquired by the data acquisition means is text data contained in electronic mail acquired from an electronic mail server.

5. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

recognition means for recognizing the language of text data acquired by the data acquisition means;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein, based on an instruction provided using the telephone, the conversion control means selects one of the plurality of speech synthesizing means and causes conversion to speech data in the selected speech synthesizing means,

wherein the conversion controller selects one of the plurality of speech synthesizing means based on a recognition result from the recognition means, and causes conversion to speech data to be carried out in the selected speech synthesizing means, and

wherein text data acquired by the data acquisition means is text data contained in electronic mail acquired from an electronic mail server.

6. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein, based on an instruction provided using the telephone, the conversion control means selects one of the plurality of speech synthesizing means and causes conversion to speech data in the selected speech synthesizing means, and

wherein text data acquired by the data acquisition means is text data contained in content acquired from a WWW server.

7. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

buffer means for holding text data acquired by the data acquisition means;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein, based on an instruction provided using the telephone, the conversion control means selects one of the plurality of speech synthesizing means and causes conversion to speech data in the selected speech synthesizing means,

wherein, if the conversion control means switches selection of the speech synthesizing means during conversion of particular text data, conversion to speech data of text data held in the buffer means is carried out in the speech synthesizing means newly selected as a result of the switch, and

wherein text data acquired by the data acquisition means is text data contained in content acquired from a WWW server.

8. A speech synthesizer comprising:

communication control means for carrying out communication between telephones on a public network;

data acquisition means for obtaining text data from a server for managing text data indicated from a telephone, when the communication control means receives a call from the telephone;

recognition means for recognizing the language of text data acquired by the data acquisition means;

a plurality of speech synthesizing means, for each of a plurality of languages, for converting text data in different languages to speech data in that language, and transmitting the speech data after conversion to the telephone via the communication control means; and

conversion control means for deciding which speech synthesizing means, among the plurality of speech synthesizing means, is to perform conversion of the text data acquired by the data acquisition means to speech data,

wherein, based on an instruction provided using the telephone, the conversion control means selects one of the plurality of speech synthesizing means and causes conversion to speech data in the selected speech synthesizing means,

wherein the conversion controller selects one of the plurality of speech synthesizing means based on a recognition result from the recognition means, and causes conversion to speech data to be carried out in the selected speech synthesizing means, and

wherein text data acquired by the data acquisition means is text data contained in content acquired from a WWW server.

9. A speech synthesizer comprising:

a circuit connection controller, the circuit connection controller providing for communications between telephone units;

a plurality of speech synthesizers, each for translating text data into speech data in a different respective language;

a call controller, the call controller controlling the operation of the circuit connection controller and the plurality of speech synthesizers, the call controller selecting a particular one of the speech synthesizers to translate the text data,

wherein the text data comprises at least one of text data from electronic mail and text data from a WWW source.

10. A speech synthesizer according to claim 9, further comprising:

a data server that receives and stores text data.

11. A speech synthesizer according to claim 10, wherein the call controller receives indication of initiation of a call from the circuit connection controller and accesses text data stored in the data server corresponding to the originator of the call.

12. The speech synthesizer according to claim 9, wherein the call controller selects one of the plurality of speech synthesizers based on information received by the circuit connection controller from an originator of a call.

13. The speech synthesizer according to claim 9, further comprising:

a header recognition section, the header recognition section determining the language content of text data, and

wherein the call controller selects one of the plurality of speech synthesizers based on the determination of language content by the header recognition section.

14. The speech synthesizer according to claim 9, wherein the call controller comprises:

a CPU, the CPU executing a control program.

15. The speech synthesizer according to claim 9, wherein each of the plurality of speech synthesizers comprises a hardware implementation of a speech synthesizer.

16. The speech synthesizer according to claim 9, wherein each of the plurality of speech synthesizers comprises a software implementation of a speech synthesizer to be executed by a CPU.

17. The speech synthesizer according to claim 9, further comprising:

a text data buffer,

wherein the text data buffer stores text data currently being synthesized by one of the plurality of speech synthesizers and thereby permitting complete speech synthesis of all text data stored therein should it be necessary to switch to a different one of the plurality of speech synthesizers.

18. A method of speech synthesis comprising the steps of:

receiving and processing an outgoing call from a telephone unit;

specifying the originator of the outgoing call;

acquiring text data corresponding to the originator of the outgoing call, the text data comprising at least one of text data from electronic mail and text data from a WWW source;

converting the text data to speech data using one of a plurality of speech synthesizers corresponding to a respective plurality of different languages; and

transmitting the speech data to the originator of the outgoing call.

19. The method according to claim 18, further comprising the steps of:

receiving an instruction from the originator of the outgoing call to use a different language to perform the step of converting;

selecting a corresponding one of the plurality of speech synthesizers corresponding to the different language; and

converting the text data to speech data using the selected one of the plurality of speech synthesizers.

20. The method according to claim 19, further comprising the step of:

buffering the text data prior to conversion,

wherein in the step of converting using the selected one of the plurality of speech synthesizers, the selected speech synthesizer converts the buffered text data.

21. The method according to claim 18, further comprising the steps of:

automatically determining the language of the text data; and

selecting one of the plurality of speech synthesizers according to the language of the text data.