METHODS AND COMPUTER PROGRAM PRODUCTS FOR PROVIDING PARAPHRASING IN A TEXT-TO-SPEECH SYSTEM

• US 20080167876A1
• Filed: 01/04/2007
• Published: 07/10/2008
• Est. Priority Date: 01/04/2007
• Status: Abandoned Application

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Eide, Ellen M., Bakis, Raimo, Picheny, Michael A., Hamza, Wael
• Application Number:
  US11/619,682
• Publication Number:
  US 20080167876A1
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/30 Semantic analysis
• 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

A method and computer program product for providing paraphrasing in a text-to-speech (TTS) system is provided. The method includes receiving an input text, parsing the input text, and determining a paraphrase of the input text. The method also includes synthesizing the paraphrase into synthesized speech. The method further includes selecting synthesized speech to output, which includes: assigning a score to each synthesized speech associated with each paraphrase, comparing the score of each synthesized speech associated with each paraphrase, and selecting the top-scoring synthesized speech to output. Furthermore, the method includes outputting the selected synthesized speech.

Claims

1. A method for paraphrasing in a text-to-speech (TTS) system, comprising:

receiving an input text;

parsing the input text;

determining a paraphrase of the input text;

synthesizing the paraphrase into synthesized speech;

selecting synthesized speech to output, comprising;

assigning a score to each synthesized speech associated with each paraphrase;

comparing the score of each synthesized speech associated with each paraphrase; and

selecting the top-scoring synthesized speech to output; and

outputting the selected synthesized speech.

2. The method of claim 1, wherein determining a paraphrase of the input text is comprised of:

searching a look-up table for a word or phrase in the input text;

finding a matching entry in the look-up table for the word or phrase in the input text; and

returning a corresponding paraphrase.

3. The method of claim 1, wherein determining a paraphrase of the input text is comprised of:

applying a rule search pattern to the input text;

finding a word or phrase that matches the rule search pattern;

applying a rule paraphrase replacement pattern; and

returning a paraphrase.

4. The method of claim 1, wherein determining a paraphrase of the input text is comprised of:

searching for a word or phrase in the input text;

finding the word or phrase in the input text;

matching a word or phrase in a foreign language translation of the input text with the word or phrase in the input text;

searching for a second instance of the matched word or phrase in the foreign language translation of the input text;

finding a second instance of the matched word or phrase in the foreign language translation of the input text;

matching a word or phrase in the input text with the second instance of the matched word or phrase in the foreign language translation of the input text; and

returning the matched word or phrase in the input text as a paraphrase.

5. The method of claim 1, wherein determining a paraphrase of the input text is comprised of:

detecting a grammatical error in a word or phrase in the input text;

determining alternate grammar for the word or phrase in the input text; and

returning the alternate grammar as a paraphrase.

6. The method of claim 1, wherein the score is a composite value comprising:

an acoustic score;

a semantic score;

a grammatical score; and

a stylistic score.

7. A computer program product for paraphrasing in a text-to-speech (TTS) system, the computer program product including instructions for implementing a method, comprising:

receiving an input text;

parsing the input text;

determining a paraphrase of the input text;

synthesizing the paraphrase into synthesized speech;

selecting synthesized speech to output, comprising;

assigning a score to each synthesized speech associated with each paraphrase;

comparing the score of each synthesized speech associated with each paraphrase; and

selecting the top-scoring synthesized speech to output; and

outputting the selected synthesized speech.

8. The computer program product of claim 7, wherein determining a paraphrase of the input text is comprised of:

searching a look-up table for a word or phrase in the input text;

finding a matching entry in the look-up table for the word or phrase in the input text; and

returning a corresponding paraphrase.

9. The computer program product of claim 7, wherein determining a paraphrase of the input text is comprised of:

applying a rule search pattern to the input text;

finding a word or phrase that matches the rule search pattern;

applying a rule paraphrase replacement pattern; and

returning a paraphrase.

10. The computer program product of claim 7, wherein determining a paraphrase of the input text is comprised of:

searching for a word or phrase in the input text;

finding the word or phrase in the input text;

matching a word or phrase in a foreign language translation of the input text with the word or phrase in the input text;

searching for a second instance of the matched word or phrase in the foreign language translation of the input text;

finding a second instance of the matched word or phrase in the foreign language translation of the input text;

matching a word or phrase in the input text with the second instance of the matched word or phrase in the foreign language translation of the input text; and

returning the matched word or phrase in the input text as a paraphrase.

11. The computer program product of claim 7, wherein determining a paraphrase of the input text is comprised of:

detecting a grammatical error in a word or phrase in the input text;

determining alternate grammar for the word or phrase in the input text; and

returning the alternate grammar as a paraphrase.

12. The computer program product of claim 7, wherein the score is a composite value comprising:

an acoustic score;

a semantic score;

a grammatical score; and

a stylistic score.