Data processing: speech signal processing – linguistics – language – Speech signal processing – Synthesis
Reexamination Certificate
2006-05-09
2006-05-09
McFadden, Susan (Department: 2655)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Synthesis
C704S243000, C704S270000, C704S008000
Reexamination Certificate
active
07043431
ABSTRACT:
There is provided a novel approach for generating multilingual text-to-phoneme mappings for use in multilingual speech recognition systems. The multilingual mappings are based on the weighted output from a neural network text-to-phoneme model, trained on data mixed from several languages. The multilingual mappings used together with a branched grammar decoding scheme is able to capture both inter- and intra-language pronunciation variations which is ideal for multilingual speaker independent recognition systems. A significant improvement in overall system performance is obtained for a multilingual speaker independent name dialing task when applying multilingual instead of language dependent text-to-phoneme mapping.
REFERENCES:
patent: 5212730 (1993-05-01), Wheatley et al.
patent: 5668926 (1997-09-01), Karaali et al.
patent: 5930754 (1999-07-01), Karaali et al.
patent: 6021387 (2000-02-01), Mozer et al.
patent: 6029132 (2000-02-01), Kuhn et al.
patent: 6085160 (2000-07-01), D'hoore et al.
patent: 6363342 (2002-03-01), Shaw et al.
patent: 2002/0040296 (2002-04-01), Kienappel
patent: 2002/0087317 (2002-07-01), Lee et al.
Sproat, “Multilingual Text Analysis for Text-to-Speech Synthesis”, 12th European Conference on Artificial Intelligence Workshop on Extended Finite State Models of Language, Budapest, Hungary, 75-81, 1996.
Jensen et al., “Self-Organizing Letter Code-Book for Text-to-Phoneme Neural Network Model”,Proceedings of ICSLP, 2000.
Palou et al., “Towards a Common Phone Alphabet for Multilingual Speech Recognition”,Proceedings of ICSLP, pp. 1-1, 2000.
Viiki et al., “Speaker- and Language-Independent Speech Recognition in Mobile Communications Systems”,Proceedings of ICASSP, 2001.
An Advanced System to Generate Pronunciations of Proper Nouns, N. Deshmukh et al.; Acoustics, IEEE International Conference, Munich, Germany, Apr. 1997, 5 pages.
Pronunciation and Acoustic Model Adaptation for Improving Multilingual Speech Recognition, J. Tian et al.; ITRW on Adaptation Methods for Speech Recognition, Aug. 2001.
Jensen Kåre Jean
Pedersen Morten With
Riis Søren
Albertalli Brian L.
Alston & Bird LLP
Nokia Corporation
LandOfFree
Multilingual speech recognition system using text derived... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Multilingual speech recognition system using text derived..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multilingual speech recognition system using text derived... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3545640