Systems and methods for selecting from multiple phonectic...

Data processing: speech signal processing – linguistics – language – Speech signal processing – Synthesis

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S258000, C704SE13002, C704SE13012

Reexamination Certificate

active

07869999

ABSTRACT:
A system and method for generating synthetic speech, which operates in a computer implemented Text-To-Speech system. The system comprises at least a speaker database that has been previously created from user recordings, a Front-End system to receive an input text and a Text-To-Speech engine. The Front-End system generates multiple phonetic transcriptions for each word of the input text, and the TTS engine uses a cost function to select which phonetic transcription is the more appropriate for searching the speech segments within the speaker database to be concatenated and synthesized.

REFERENCES:
patent: 5682501 (1997-10-01), Sharman
patent: 5740320 (1998-04-01), Itoh
patent: 5796916 (1998-08-01), Meredith
patent: 6148285 (2000-11-01), Busardo
patent: 6163769 (2000-12-01), Acero et al.
patent: 6173263 (2001-01-01), Conkie
patent: 6178402 (2001-01-01), Corrigan
patent: 6230131 (2001-05-01), Kuhn et al.
patent: 6363342 (2002-03-01), Shaw et al.
patent: 6366883 (2002-04-01), Campbell et al.
patent: 6665641 (2003-12-01), Coorman et al.
patent: 6684187 (2004-01-01), Conkie
patent: 6950798 (2005-09-01), Beutnagel et al.
patent: 6961704 (2005-11-01), Phillips et al.
patent: 6988069 (2006-01-01), Phillips
patent: 7013278 (2006-03-01), Conkie
patent: 7277851 (2007-10-01), Henton
patent: 7333932 (2008-02-01), Hain
patent: 7496498 (2009-02-01), Chu et al.
patent: 7630898 (2009-12-01), Davis et al.
patent: 2002/0077820 (2002-06-01), Simpson
patent: 2002/0099547 (2002-07-01), Chu et al.
patent: 2002/0103648 (2002-08-01), Case et al.
patent: 2003/0069729 (2003-04-01), Bickley et al.
patent: 2003/0130848 (2003-07-01), Sheikhzadeh-Nadjar et al.
patent: 2003/0158734 (2003-08-01), Cruickshank
patent: 2003/0163316 (2003-08-01), Addison et al.
patent: 2003/0191645 (2003-10-01), Zhou
patent: 2004/0024600 (2004-02-01), Hamza et al.
patent: 2004/0111266 (2004-06-01), Coorman et al.
patent: 2004/0153324 (2004-08-01), Phillips
patent: 2004/0193398 (2004-09-01), Chu et al.
patent: 2005/0182629 (2005-08-01), Coorman et al.
patent: 2005/0197838 (2005-09-01), Lin et al.
patent: 2006/0031069 (2006-02-01), Huang et al.
Jelinek, Frederick. 1976. Continuous speech recognition by statistical methods. IEEE. 532-556.
M. Lee, D.P. Lopresti, and J.P. Olive, “A Text-to-Speech Platform for Variable Length Optimal Unit Searching Using Perceptual Cost Functions,” Proc. ISCA Research Workshop Speech Synthesis, pp. 347-356, Aug.-Sep. 2001.
Abhinav Sethy, Shrikanth Narayanam, “Refined speech segmentation for concatenative speech synthesis,” Proc. ICSLP, pp. 145-148,2002.
A. Hunt and A. Black, “Unit selection in a concatenative speech synthesis system using large speech database,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, 1996, pp. 373-376.
Yeon-Jun Kim and Ann Syrdal. 2004. Improving tts by higher agreement between predicted versus observed pronunciations. In Fifth ISCA ITRW on Speech Synthesis (SSW5), Pittsburgh, PA, USA.
Kim et al. “Pronunciation Lexicon Adaptation for TTS Voice Building”, Oct. 4-8, 2004.
Fackrell et al. “Improving the accuracy of pronunciation prediction for unit selection TTS”, 2003.
Rutten et al. “The application of interactive speech unit selection in TTS systems”, 2003.
Toda et al. “Optimizing Integrated Cost Function for Segment Selection in Concatenative Speech Synthesis Based on Perceptual Evaluations” 2003.
Peng et al. “Perpetually Optimizing the Cost Function for Unit Selection in a TTS System With One Single Run of MOS Evaluation” 2002.
Hamza et al. “Reconciling Pronunciation Differences Between the Frontend and Back-End in the IBM Speech Synthesis System” Oct. 2004.
Crepy, H., et al., “Optimisation d'arbres de decision pour la conversion graphemes-phonemes”, Proc. of XXIVemes Journees d'Etude sur la Parole, Nancy, (2002).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Systems and methods for selecting from multiple phonectic... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Systems and methods for selecting from multiple phonectic..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Systems and methods for selecting from multiple phonectic... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2684864

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.