Prosody template matching for text-to-speech systems

Details Prosody template matching for text-to-speech systems Prosody template matching for text-to-speech systems

2005-01-18

2005-01-18

To, Doris H. (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Synthesis

C704S266000, C704S010000

Reexamination Certificate

active

06845358

ABSTRACT:
A prosody matching template in the form of a tree structure stores indices which point to lookup table and template information prescribing pitch and duration values that are used to add inflection to the output of a text-to-speech synthesizer. The lookup module employs a search algorithm that explores each branch of the tree, assigning penalty scores based on whether the syllable represented by a node of the tree does or does not match the corresponding syllable of the target word. The path with the lowest penalty score is selected as the index into the prosody template table. The system will add nodes by cloning existing nodes in cases where it is not possible to find a one-to-one match between the number of syllables in the target word and the number of nodes in the tree.

REFERENCES:
patent: 5384893 (1995-01-01), Hutchins
patent: 5625749 (1997-04-01), Goldenthal et al.
patent: 5652828 (1997-07-01), Silverman
patent: 5890117 (1999-03-01), Silverman
patent: 5905972 (1999-05-01), Huang et al.
patent: 5915237 (1999-06-01), Boss et al.
patent: 6029132 (2000-02-01), Kuhn et al.
patent: 6052664 (2000-04-01), Van Coile et al.
patent: 6055498 (2000-04-01), Neumeyer et al.
patent: 6101470 (2000-08-01), Eide et al.
patent: 6163769 (2000-12-01), Acero et al.
patent: 6185533 (2001-02-01), Holm et al.
patent: 6260016 (2001-07-01), Holm et al.
patent: 6266637 (2001-07-01), Donovan et al.
patent: 6438522 (2002-08-01), Minowa et al.
patent: 6490563 (2002-12-01), Hon et al.
patent: 20010018654 (2001-08-01), Hon et al.
patent: 20010044724 (2001-11-01), Hon et al.
patent: 0833304 (1998-04-01), None
patent: 0953970 (1999-11-01), None
patent: 07-311588 (1995-11-01), None
patent: 8-044391 (1996-02-01), None
patent: 08-263260 (1996-10-01), None
patent: 10-171485 (1998-06-01), None
patent: 2000-310995 (2000-11-01), None
Iverson et al (“An Experiment Of Surface Recognition By Neural Trees”, Computer Architectures for Machine Perception proceedings, Sep. 1995).*
Lee et al (“Voice Response Systems”, ACM Computing Surveys (CSUR), Dec. 1983).*
Levine (“Prosodic Generation Research”, Proceedings of the Annual Conference, Oct. 1976).*
Chung-Hsien et al (“Template-Driven Generation Of Prosodic Information For Chinese Concatenative Synthesis”, IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar. 1999).*
Huang et al (“Recent Improvements On Microsoft's Trainable Text-To-Speech System—Whistler”, IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr. 1997).*
Chung-Hsien Wu, Jau-Hung Chen, “Template-Driven Generation of Prosodic Information for chinese Concatenative Synthesis”, 1999 IEEE International Conference on Acoustics, Speech, adn Signal Processing. Phoenix, AZ, Mar. 15-19, 1999, IEEE Internation Conference on Acoustics, Speech, and signal Processign (ICASSP), New York, NY.

Affiliated with

Also associated with

Rating

Prosody template matching for text-to-speech systems does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Prosody template matching for text-to-speech systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Prosody template matching for text-to-speech systems will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3387719