Data processing: speech signal processing – linguistics – language – Speech signal processing – Synthesis
Reexamination Certificate
2008-07-29
2008-07-29
Armstrong, Angela A (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Synthesis
C704S266000
Reexamination Certificate
active
07406417
ABSTRACT:
A neural network can be trained for synthesizing or recognizing speech with the aid of a database produced by automatically matching graphemes and phonemes. First, graphemes and phonemes are matched for words which have the same number of graphemes and phonemes. Next, graphemes and phonemes are matched for words that have more graphemes than phonemes in a series of steps that combine graphemes with preceding phonemes. Then, graphemes and phonemes are matched for words that have fewer graphemes than phonemes. After each step, infrequent and unsuccessful matches made in the preceding step are are erased. After this process is completed, the database can be used to train the neural network and graphemes, or letters of a text can be converted into the corresponding phonemes with the aid of the trained neural network.
REFERENCES:
patent: 6304845 (2001-10-01), Hünlich et al.
patent: 6411932 (2002-06-01), Molnar et al.
patent: 68913669 (1994-07-01), None
patent: 197 51 123 (1999-06-01), None
patent: 372 734 (1990-06-01), None
patent: 99/40568 (1999-08-01), None
Luk et al., “Inference of Letter-Phoneme Correspondences by Delimiting and Dynamic Time Warping Techniques”, Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 17, Mar. 23, 1992, pp. 61-64.
Oakey et al., “Inductive Learning of Pronunciation Rules by Hypothesis Testing and Correction”, Proceedings of the 7th Joint Conference on Artificial Intelligence IJCA1-81, Aug. 24-28, 1981, pp. 109-114.
Torkkola et al., “Dynamically Expanding Context vs. Multi-Layered Networks in Correction of Phoneme Strings”, Proceedings of the Expert Systems Applications World Conference, IITT International, vol. Conf. 1, 1989, pp. 333-337.
Dutoit, “Introduction to Text-to-Speech Synthesis”, 1997, Kluwers Academic XP002157980, paragraph 5.4.3.
Armstrong Angela A
Siemens Aktiengesellschaft
Staas & Halsey , LLP
LandOfFree
Method for conditioning a database for automatic speech... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for conditioning a database for automatic speech..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for conditioning a database for automatic speech... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2787920