Text-to-speech system and a method and apparatus for training th

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

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G10L 500

Patent

active

060030054

ABSTRACT:
A method of training a TTS or other system to assign intonational features, such as intonational phrase boundaries, to input text that overcome the shortcomings of the known methods is described. The method of training involves taking a set of predetermined text (not speech or a signal representative of speech) and having a human annotate it with intonational feature annotations. This results in annotated text. Next, the structure of the set of predetermined text is analyzed to generate information. This information is used, along with the intonational feature annotations, to generate a statistical representation. The statistical representation may then be stored and repeatedly used to generate synthesized speech from new sets of input text without training the TTS system further. The resulting trained system and use thereof are also part of the invention.

REFERENCES:
patent: 4829580 (1989-05-01), Church
patent: 4979216 (1990-12-01), Malsheen et al.
patent: 5075896 (1991-12-01), Wilcox et al.
patent: 5146405 (1992-09-01), Church
patent: 5212730 (1993-05-01), Wheatley et al.
patent: 5230037 (1993-07-01), Giustiniani et al.
patent: 5267345 (1993-11-01), Brown et al.
patent: 5774854 (1998-06-01), Sharman
patent: 5796916 (1998-08-01), Meredith
patent: 5890117 (1999-03-01), Silverman
Computer Speech and Language. Wnag et al. "Automatic classification of intonational phrase boundaries". vol. 6, No. 2, pp. 175-196, Apr. 1992.
Eurospeech 91. Hirshchberg, "Using text analysis to predict intonational boundaries", pp. 1275-1278, Sep. 1991.
M.Q. Wang et al., "Predicting Intonational Boundaries Automatically From Text: The ATIS Domain," (DARPA 1991) pp. 378-383.
R. Sproat et al., "A Corpus-Based Synthesizer," pp. 563-566. No date.
M.Q. Wang et al., "Automatic Classification of Intonational Phrase Boundaries," Computer Speech and Language, vol. 6, 1992, pp. 175-196.
N.M. Veilleux et al., "Markov Modeling Of Prosodic Phrase Structure," IEEE, 1990, pp. 777-780.
E. Brill et al., "Deducing Linguistic Structure From the Statistics Of Large Corpora," IEEE, 1990, pp. 380-389.

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

Text-to-speech system and a method and apparatus for training th does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Text-to-speech system and a method and apparatus for training th, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Text-to-speech system and a method and apparatus for training th will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-873378

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