Speech synthesis with incremental databases of speech waveforms on user terminals over a communications network

• US 8,583,437 B2
• Filed: 05/31/2005
• Issued: 11/12/2013
• Est. Priority Date: 05/31/2005
• Status: Active Grant

• Current Assignee: Telecom Italia S.p.A.
• Original Assignee: Telecom Italia S.p.A.
• Inventors: Collotta, Ivano Salvatore, Ettorre, Donato, Fodrini, Maurizio, Turolla, Maura, Cervone, Alessio, Coppo, Paolo
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US11/921,403
• Publication Number:
  US 20090306986A1
• Time in Patent Office: 3,087 Days
• Field of Search: 704/258, 704/260, 704/261, 704/266, 704/269, 704/270.1, 379/88.16, 379/88.17, 379/88.23
• US Class Current: 704/258
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

Service architecture for providing to a user terminal of a communications network textual information and relative speech synthesis, the user terminal being provided with a speech synthesis engine and a basic database of speech waveforms includes: a content server for downloading textual information requested by means of a browser application on the user terminal; a context manager for extracting context information from the textual information requested by the user terminal; a context selector for selecting an incremental database of speech waveforms associated with extracted context information and for downloading the incremental database into the user terminal; a database manager on the user terminal for managing the composition of an enlarged database of speech waveforms for the speech synthesis engine including the basic and the incremental databases of speech waveforms.

Claims

1. A method of generating synthesized speech from textual information on a user terminal, said user terminal being provided with a speech synthesis engine having a basic database of speech waveforms, comprising the steps of:

starting speech synthesis of said textual information employing said basic database of speech waveforms;

sending to a context server a request related to the textual information to be synthesized, the request seeking an incremental database based on a context of said textual information to be synthesized, wherein the context is to be determined from context information extracted from said textual information to be synthesized;

receiving the incremental database of speech waveforms associated with said context;

managing the composition of an enlarged database of speech waveforms comprising said basic and said incremental databases of speech waveforms; and

continuing speech synthesis of said textual information employing said enlarged database of speech waveforms, wherein at least part of the basic database and at least part of the incremental database are used to synthesize the speech.

2. The method of claim 1, wherein said step of receiving said incremental database comprises:

downloading, through a communications network, said incremental database from said context server, if said incremental database is not already present in said user terminal.

3. The method of claim 2, wherein said step of downloading said incremental database into said user terminal comprises:

downloading an incremental database of speech waveforms; and

updating a descriptor file of said enlarged database of speech waveforms.

4. The method of claim 1, further comprising the step of storing said incremental database into a cache memory on said user terminal.

5. The method of claim 1, wherein said request seeks an incremental database of speech waveforms associated with said context information selected according to context rules independent of user profiles.

6. The method of claim 1, wherein said request seeks an incremental database of speech waveforms associated with said context information selected according to context rules based on a user profile.

7. The method of claim 1, wherein said textual information is retrieved by said user terminal through a communications network.

8. The method of claim 1, comprising the step of:

replacing said basic database of speech waveforms by downloading, through a communications network, a substitute basic database into said user terminal.

9. The method of claim 8, wherein said communications network is a wireless telecommunication network.

10. A non-transitory computer readable medium encoded with a computer program product, loadable into a memory of at least one computer and comprising software code portions for performing the method of claim 1.

11. A communications system for synthesizing speech from textual information, comprising:

a user terminal, the user terminal further comprising;

a speech synthesis engine,

a basic database of speech waveforms, and

a database manager for managing the composition of an enlarged database of speech waveforms for said speech synthesis engine comprising said basic database of speech waveforms and an incremental database of speech waveforms; and

a context server for downloading, over a communications network, said incremental database of speech waveforms into said user terminal, said incremental database being based on a context of said textual information to be synthesized determined from context information extracted from said textual information to be synthesized; and

wherein the speech synthesis engine is configured to use at least part of the basic database and at least part of the incremental database to synthesize the speech, said speech synthesis engine starting speech synthesis of said textual information employing said basic database of speech waveforms and continuing speech synthesis of said textual information employing said enlarged database of speech waveforms.

12. The communications system of claim 11, wherein said context server comprises:

a context manager for extracting context information from said textual information; and

a context selector for selecting said incremental database of speech waveforms associated with said context information and for downloading said incremental database into said user terminal.

13. The communications system of claim 12, further comprising a database server storing a plurality of incremental databases selected by said context selector.

14. The communications system of claim 12, wherein said context selector operates according to context rules independent of user profiles.

15. The communications system of claim 12, wherein said context selector operates according to context rules based on a user profile.

16. The communications system of claim 11, wherein said user terminal further comprises a cache memory for temporarily storing at least one downloaded incremental database.

17. The communications system of claim 11, further comprising a content server for downloading said textual information into said user terminal.

18. The communications system of claim 11, wherein said communications network is a wireless telecommunication network.

19. A user terminal of a communications network comprising:

a speech synthesis engine;

a basic database of speech waveforms; and

an application for retrieving textual information to be converted into synthesized speech comprising;

a database manager configured to;

download an incremental database of speech waveforms from a database server, said incremental database being based on a context of said textual information to be synthesized determined from context information extracted from said textual information to be synthesized, and

manage the composition of an enlarged speech waveforms database for said speech synthesis engine, comprising said basic and said incremental databases of speech waveforms,

wherein the speech synthesis engine is configured to use at least part of the basic database and at least part of the incremental database to synthesize the speech, said speech synthesis engine starting speech synthesis of said textual information employing said basic database of speech waveforms and continuing speech synthesis of said textual information employing said enlarged database of speech waveforms.

20. The user terminal of claim 19, further comprising a cache memory for temporarily storing at least one downloaded incremental database.

21. The user terminal of claim 19, wherein said speech synthesis engine is based on concatenative speech synthesis.