Claims
- 1. A method for generating the phonetico-prosodic parameters of a predetermined message starting from a source message, said predetermined message being formed by at least one carrier, each carrier comprising at least one fixed part and at least one open slot, an argument having been inserted in each open slot, said method comprising:
- a) applying a prosody transplantation technique to said source message in order to obtain a sequence of phonetico-prosodic parameters for each carrier;
- b) identifying in each sequence sections of phonetico-prosodic parameters corresponding to said arguments;
- c) substituting each of said sections by open slot data comprising at least position information indicating the position of the open slots;
- d) assigning to each thus obtained sequence an identifier;
- e) storing the thus obtained sequences with their identifiers in a memory for subsequent use in generation of speech.
- 2. A method according to claim 1, wherein said predetermined message further comprises at least one phrase, said method further comprising:
- a) applying a prosody transplantation technique to each of said phrases in order to obtain a further sequence of phonetico-prosodic parameters for each of said phrases;
- b) assigning to each of said further sequences each time a further identifier;
- c) storing the thus obtained further sequences with their respective further identifier in said memory.
- 3. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 2, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in orthographic form each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said orthographic form;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers with their arguments into speech.
- 4. A method for electronically generating a spoken message according to claim 3, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 5. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 2, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers:
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said phonetic transcription;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers and phrases with their arguments into speech.
- 6. A method for electronically generating a spoken message according to claim 5, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 7. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 2, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in orthographic form and/or phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said argument;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers and phrases with their arguments into speech.
- 8. A method for electronically generating a spoken message according to claim 7, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 9. A method according to claim 2, wherein upon applying said prosody transplantation enriched phonetic transcription is generated.
- 10. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 9, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in orthographic form each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating enriched phonetic transcription from said orthographic form;
- f) filling in said enriched phonetic transcription of said arguments in their assigned open slots;
- g) transforming said enriched phonetic transcription of said carriers and phrases with their arguments into speech.
- 11. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 9, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating enriched phonetic transcription from said phonetic transcription;
- f) filling in said enriched phonetic transcription of said arguments in their assigned open slots;
- g) transforming said enriched phonetic transcription of said carriers and phrases with their arguments into speech.
- 12. A method according to claim 1, wherein at least one of the following characteristics
- lexical information of the open slot,
- syntactical information of the open slot,
- intonation model of the open slot,
- is determined for each of said sections and each time added to the open slot data of the sequence.
- 13. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 12, said method comprises:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in orthographic form each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said orthographic form and according to said characteristics;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said. phonetico-prosodic parameters of said carriers with their arguments into speech.
- 14. A method for electronically generating a spoken message according to claim 13, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 15. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 12, said method comprises:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory
- d) supplying in phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said phonetic transcription and according to said characteristics;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers with their arguments into speech.
- 16. A method for electronically generating a spoken message according to claim 15, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 17. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 12, said method comprises:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in orthographic form and/or phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said argument and according to said characteristics;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said. phonetico-prosodic parameters of said carriers with their arguments into speech.
- 18. A method for electronically generating a spoken message according to claim 17, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 19. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 1, said method comprising:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in orthographic form each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said orthographic form;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers with their arguments into speech.
- 20. A method for electronically generating a spoken message according to claim 19, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 21. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 1, said method comprises:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers:
- e) generating phonetico-prosodic parameters from said phonetic transcription;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers with their arguments into speech.
- 22. A method for electronically generating a spoken message according to claim 21, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 23. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 1, said method comprising:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in orthographic form and/or phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said argument and according to said characteristics;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers with their arguments into speech.
- 24. A method for electronically generating a spoken message according to claim 23, wherein said message is formed by at least two carriers which are concatenated before being transformed into speech.
- 25. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 24, said method comprising:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in orthographic form and/or phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating phonetico-prosodic parameters from said arguments;
- f) filling in said phonetico-prosodic parameters of said arguments in their assigned open slots;
- g) transforming said phonetico-prosodic parameters of said carriers with their arguments into speech.
- 26. A method according to any claim 1, wherein upon applying said prosody transplantation enriched phonetic transcription is generated.
- 27. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 26, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in orthographic form each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating enriched phonetic transcription from said orthographic form;
- f) filling in said enriched phonetic transcription ot said arguments in their assigned open slots:
- g) transforming said enriched phonetic transcription of said carriers and phrases with their arguments into speech.
- 28. A method for electronically generating a spoken message, starting from phonetico-prosodic parameters generated by application of the method according to claim 26, said method comprising:
- a) selecting those carriers and phrases composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers and phrases by means of their assigned identifiers;
- c) reading said addressed carriers and phrases from said memory;
- d) supplying in phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating enriched phonetic transcription from said phonetic transcription;
- f) filling in said enriched phonetic transcription of said arguments in their assigned open slots:
- g) transforming said enriched phonetic transcription of said carriers and phrases with their arguments into speech.
- 29. A method for electronically generating a spoken message, starting from enriched phonetic transcription generated by application of the method according to claim 26, said method comprising:
- a) selecting those carriers composing the message to be generated and generating the identifiers assigned to said selected carriers;
- b) addressing in said memory said selected carriers by means of their assigned identifiers;
- c) reading said addressed carriers from said memory;
- d) supplying in orthographic form and/or phonetic transcription each argument to be filled in in said open slots of said selected carriers and assigning each argument to a respective open slot within said selected carriers;
- e) generating enriched phonetic transcription from said arguments;
- f) filling in said. enriched phonetic transcription of said arguments in their assigned open slots;
- g) transforming said enriched phonetic transcription of said carriers with their arguments into speech.
- 30. An improved apparatus for generating a spoken message of the type employing a source message, the source message being parsed into at least one carrier, each carrier having at least one fixed part and at least one open slot, an argument being inserted into each open slot, wherein the improvement comprises:
- a. a phonetico-prosodic parameter generator for characterizing the message in terms of phonetico-prosodic parameters;
- b. an electronic memory for storing phonetico-prosodic parameters corresponding to each carrier;
- c. a controller for constructing sequences of phonetico-prosodic parameters corresponding to the argument of each open slot;
- d. a phonetics-to-speech converter for generating a digital sound wave pattern from the sequences of phonetico-prosodic parameters;
- e. a D/A converter for generating an analog sound wave pattern from the digital sound wave pattern; and
- f. an output unit for providing audible sound waves corresponding to the analog sound wave pattern.
- 31. An apparatus according to claim 30, further comprising an input device for reading an argument in orthographic or phonetic text tormat.
- 32. An apparatus for electronically generating a spoken message from phonetico-prosodic parameters, the spoken message having at least one carrier, each carrier having at least one fixed part and at least one open slot, an argument being inserted into each open slot, the apparatus comprising:
- a. a first controller for selecting at least one carrier to form the spoken message;
- b. an electronic memory for storing phonetico-prosodic parameters corresponding to each carrier;
- c. a second controller for constructing sequences of phonetico-prosodic parameters corresponding to the argument of each open slot;
- d. a phonetics-to-speech converter for generating a digital sound wave pattern from the sequences of phonetico-prosodic parameters and each selected carrier;
- e. a D/A converter for generating an analog sound wave pattern from the digital sound wave pattern; and
- f. an output unit for providing audible sound waves corresponding to the analog sound wave pattern.
Parent Case Info
This application is a continuation application of Ser. No. 08/725,881, filed Oct. 4, 1996, now U.S. Pat. No. 5,727,120, which is a divisional application of Ser. No. 08/379,330, filed Jan. 26, 1995, now U.S. Pat. No. 5,592,585, incorporated herein by reference.
US Referenced Citations (2)
Number |
Name |
Date |
Kind |
5592585 |
Van Coile et al. |
Jan 1997 |
|
5727120 |
Van Coile et al. |
Mar 1998 |
|
Divisions (1)
|
Number |
Date |
Country |
Parent |
379330 |
Jan 1995 |
|
Continuations (1)
|
Number |
Date |
Country |
Parent |
725881 |
Oct 1996 |
|