Method and apparatus for preparing a document to be read by text-to-speech reader

• US 7,953,601 B2
• Filed: 12/19/2008
• Issued: 05/31/2011
• Est. Priority Date: 06/28/2002
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Pickering, John B.
• Primary Examiner(s): Rider; Justin W
• Application Number:
  US12/339,803
• Publication Number:
  US 20090099846A1
• Time in Patent Office: 893 Days
• Field of Search: 704/260
• 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

There is disclosed a method and system for preparing a document to be read by a text-to-speech reader. The method can include identifying two or more voice types available to the text-to-speech reader, identifying the text elements within the document, grouping related text elements together, and classifying the text elements according to voice types available to the text-to-speech reader. The method of grouping the related text elements together can include syntactic and intelligent clustering. The classification of text elements can include performing latent semantic analysis on the text elements and characteristics of the available voice types.

Claims

1. A system for automatically marking a document to be read by a text-to-speech reader with voice type identifiers, said system comprising:

at least one processor programmed to;

identify two or more voice types available to the text-to-speech reader, each voice type having a corresponding voice type identifier;

identify text elements within the document by marking gross structural subdivisions of text with a first set of sequenced tags, marking individual paragraphs of the text with a second set of sequenced tags, and marking text elements with a third set of sequenced tags to generate a hierarchical tree identifying the text elements;

group similar text elements together by generating one or more clusters according to each identifiable topic of the document, and by syntactically parsing the document and subsequently performing text mining to determine which text elements in the document are similar, wherein similarity is based upon lexical affinities among the text elements;

classify the grouped text elements according to voice types available to the text-to-speech reader; and

mark the classified grouped text elements within the document with corresponding voice type identifiers.

2. The system as claimed in claim 1, wherein the at least one processor is programmed to identify text elements by breaking down the document into elements and by separating out the text elements.

3. The system as claimed in claim 1, wherein the at least one processor is programmed to group similar text elements together by parsing for structural features of the text elements.

4. The system as claimed in claim 3, wherein the structural features of the text elements include at least one feature selected from the group consisting of:

the position of the text element in the document, the syntax of the text element, and text features within the text element.

5. The system as claimed in claim 3, wherein the at least one processor is programmed to group similar text elements by parsing for thematic features of the text elements.

6. The system as claimed in claim 1, wherein the at least one processor is programmed to classify the text elements according to the available voice types by finding the best match between the grouped text elements and the characteristics of the voice types.

7. The system as claimed in claim 6, wherein the at least one processor is programmed to classifying the text elements according to the characteristics of the available voice types by identifying similar themes within the text elements and voice types.

8. The system as claimed in claim 6, wherein the at least one processor is programmed to classify the text elements according to the characteristics of the available voice types by identifying similar intentions within the text elements and voice types.

9. A non-transitory computer-readable storage medium, encoded with computer program instructions that, when executed by a machine, cause the machine to perform a method for automatically marking a document to be read by a text-to-speech reader with voice type identifiers, the method comprising:

identifying two or more voice types available to the text-to-speech reader, each voice type having a corresponding voice type identifier;

identifying text elements within the document, wherein identifying text elements comprises marking gross structural subdivisions of text with a first set of sequenced tags, marking individual paragraphs of the text with a second set of sequenced tags, and marking text elements with a third set of sequenced tags to generate a hierarchical tree identifying the text elements;

grouping similar text elements together, wherein grouping comprises generating one or more clusters according to each identifiable topic of the document, syntactically parsing the document and subsequently performing text mining to determine which text elements in the document are similar, wherein similarity is based upon lexical affinities among the text elements;

classifying the grouped text elements according to voice types available to the text-to-speech reader; and

marking the classified grouped text elements within the document with corresponding voice type identifiers.

10. The non-transitory computer-readable storage medium as claimed in claim 9, wherein identifying text elements further comprises breaking down the document into elements and code for separating out the text elements.

11. The non-transitory computer-readable storage medium as claimed in claim 9, wherein grouping similar text elements together further comprises parsing for structural features of the text elements.

12. The non-transitory computer-readable storage medium as claimed in claim 11, wherein the structural features of the text elements include at least one feature selected from the group consisting of:

the position of the text element in the document, the syntax of the text element, and text features within the text element.

13. The non-transitory computer-readable storage medium as claimed in claim 11, wherein grouping similar text elements together further comprises parsing for thematic features of the text elements.

14. The non-transitory computer-readable storage medium as claimed in claim 9, wherein classifying the text elements according to the available voice types further comprises finding the best match between the grouped text elements and the characteristics of the voice types.

15. The non-transitory computer-readable storage medium as claimed in claim 14, wherein classifying the text elements according to the characteristics of the available voice types further comprises identifying similar themes within the text elements and voice types.

16. The non-transitory computer-readable storage medium as claimed in claim 14, wherein classifying the text elements according to the characteristics of the available voice types further comprises identifying similar intentions within the text elements and voice types.