Method for guiding text-to-speech output timing using speech recognition markers

• US 7,010,489 B1
• Filed: 03/09/2000
• Issued: 03/07/2006
• Est. Priority Date: 03/09/2000
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Lewis, James R., Ortega, Kerry A., Wang, Huifang
• Primary Examiner(s): ARMSTRONG, ANGELA A
• Application Number:
  US09/521,593
• Time in Patent Office: 2,189 Days
• Field of Search: 704/270, 704/260, 704/258, 704/256, 704/257, 704/255
• US Class Current: 704/260
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A method for guiding text-to-speech output timing with speech recognition markers can include the following steps. First, tokens can be retrieved in a TTS system. The tokens can include words, phrase markers, punctuation marks and meta-tags. Second, phrase markers can be identified among the retrieved tokens. Third, words can be identified among the retrieved tokens. Fourth, the TTS system can TTS play back the identified words. Finally, during the TTS playback of the words, the TTS system can pause in response to the identification of the phrase markers.

Claims

1. A method for guiding text-to-speech output timing with speech recognition markers comprising the steps of:

retrieving tokens in a text-to-speech (TTS) system, said tokens comprising words, phrase markers, punctuation marks and meta-tags;

identifying said phrase markers among said retrieved tokens, said phrase markers specifying timing information corresponding to previously dictated speech;

identifying said words among said retrieved tokens;

playing back said identified words using said TTS system; and

,

pausing said TTS playback in response to said identification of said phrase markers in accordance with said specified timing information.

2. The method according to claim 1, further comprising the steps of:

identifying said punctuation marks among said retrieved tokens; and

,

pausing in response to said identification of said punctuation marks.

3. The method according to claim 2, wherein said step of pausing in response to said identification of a punctuation mark comprises the steps of:

classifying said identified punctuation mark into a punctuation class;

pausing for a programmatically determined length of time corresponding to said punctuation class.

4. The method according to claim 3, wherein said punctuation class is a class selected from the group consisting of sentence internal markers and sentence final markers.

5. The method according to claim 1, wherein said pausing step comprises the steps of:

identifying pause duration data embedded in said phrase marker; and

,

pausing for a period of time corresponding to said pause duration data.

6. The method according to claim 1, wherein said pausing step comprises the step of pausing for a programmatically determined length of time.

7. The method according to claim 1, wherein said pausing step comprises the steps of:

retrieving a user playback preference;

if said retrieved user playback preference indicates a user preference for realistic playback, pausing for a period of time corresponding to pause duration data stored with said phrase marker; and

,

if said retrieved user playback preference indicates a user preference for streamlined playback, pausing for a programmatically determined length of time.

8. The method according to claim 1, further comprising the steps of:

identifying said meta-tags among said retrieved tokens; and

,

pausing in response to said identification of said meta-tags.

9. The method according to claim 1, wherein said TTS playing back step comprises the step of TTS playing back said tokens using TTS production rules.

10. The method according to claim 1, wherein said pausing step comprises the steps of:

delaying TTS playback for a period of time corresponding to a programmable upper limit on pause length; and

,

resuming TTS playback subsequent to said period of time.

11. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

retrieving tokens in a text-to-speech (TTS) system, said tokens comprising words, phrase markers, punctuation marks and meta-tags;

identifying said phrase markers among said retrieved tokens, said phrase markers specifying timing information corresponding to previously dictated speech;

identifying said words among said retrieved tokens;

playing back said identified words using said TTS system; and

,

pausing said TTS playback in response to said identification of said phrase markers in accordance with said specified timing information.

12. The machine readable storage according to claim 11, further comprising the steps of:

identifying said punctuation marks among said retrieved tokens; and

,

pausing in response to said identification of said punctuation marks.

13. The machine readable storage according to claim 12, wherein said step of pausing in response to said identification of a punctuation mark comprises the steps of:

classifying said identified punctuation mark into a punctuation class;

pausing for a programmatically determined length of time corresponding to said punctuation class.

14. The machine readable storage according to claim 13, wherein said punctuation class is a class selected from the group consisting of sentence internal markers and sentence final markers.

15. The machine readable storage according to claim 11, wherein said pausing step comprises the steps of:

identifying pause duration data embedded in said phrase marker; and

,

pausing for a period of time corresponding to said pause duration data.

16. The machine readable storage according to claim 11, wherein said pausing step comprises the step of pausing for a programmatically determined length of time.

17. The machine readable storage according to claim 11, wherein said pausing step comprises the steps of:

retrieving a user playback preference;

if said retrieved user playback preference indicates a user preference for realistic playback, pausing for a period of time corresponding to pause duration data stored with said phrase marker; and

,

if said retrieved user playback preference indicates a user preference for streamlined playback, pausing for a programmatically determined length of time.

18. The machine readable storage according to claim 11, further comprising the steps of:

identifying said meta-tags among said retrieved tokens; and

,

pausing in response to said identification of said meta-tags.

19. The machine readable storage according to claim 11, wherein said TTS playing back step comprises the step of TTS playing back said tokens using TTS production rules.

20. The machine readable storage according to claim 11, wherein said pausing step comprises the steps of:

delaying TTS playback for a period of time corresponding to a programmable upper limit on pause length; and

,

resuming TTS playback subsequent to said period of time.