Methods for speech processing

Details Methods for speech processing Methods for speech processing

2005-07-19

2005-07-19

Abebe, Daniel (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S235000

Reexamination Certificate

active

06920423

ABSTRACT:
The invention relates to a method for speech processing in which input variables containing speech features are mapped onto output variables. In the mapping process, the input variables are weighted and/or identical maps are produced for different sets of input variables and at least one output variable.

REFERENCES:
patent: 4912655 (1990-03-01), Wood
patent: 5398300 (1995-03-01), Levey
patent: 5479563 (1995-12-01), Yamaguchi
patent: 5732388 (1998-03-01), Hoege et al.
patent: 6029135 (2000-02-01), Krasle
patent: 6216048 (2001-04-01), Keeler et al.
patent: 6581048 (2003-06-01), Werbos
A. Krogh et al., “A Simple Weight Decay can Improve Generalization”, Advances In Neural Information Processing Systems 4, 1995, pp. 950-957.
G. P. Sonntag et al., “Prosody Generation with an Neural Network: Weighing the Importance of Input Parameters”, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1997, pp. 931-934.
Ralf Haury et al., “Optimization of a Neural Network for Speaker and Task Dependent F0-Generation”, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1998, pp. 297-300.
C. Erdem et al., “Soft Input Feature Selection within Neural Prosody Generation”, Speech Prosody 2002, Apr. 13, 2002, 4 pages.
Hirschberg et al., “Training Intonational Phrasing Rules Automatically for English and Spanish Text-to-Speech”, Speech Communication 18, 1996, pp. 281-290.
Wang et al., “Automatic Classification of Intonational Phrase Boundaries”, Computer Speech and Language 6, 1992, pp. 175-196.
Black et al., “Assigning Phrase Breaks from Part-of-Speech Sequences”, Eurospeech, 1997.
Muller et al., “Robust Generation of Symbolic Prosody by a Neural Classifier Based on Autoassociators”, ICASSP, 2000.
Hirschberg, “Pitch Accent in Context Predicting Intonational Prominence From Text”, Artifical Intelligence 63, 1993, pp. 305-340.
Widera et al., “Prediction of Word Prominence”, Eurospeech, 1997.
Sonntag et al., “Prosody Generation with a Neural Network: Weighing the Importance of Input Parameters”, ICASSP, 1997.
Jianhua et al., “A Neural Network Based Prosodic Model of Mandarin TTS System”, ICSLPS, 2000.

Affiliated with

Also associated with

Rating

Methods for speech processing does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Methods for speech processing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods for speech processing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3368495