Method of setting optimum-partitioned classified neural...

Data processing: speech signal processing – linguistics – language – Speech signal processing – For storage or transmission

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S201000, C704S232000, C704S243000, C704S259000, C706S020000, C706S025000

Reexamination Certificate

active

07444282

ABSTRACT:
A method of automatic labeling using an optimum-partitioned classified neural network includes searching for neural networks having minimum errors with respect to a number of L phoneme combinations from a number of K neural network combinations generated at an initial stage or updated, updating weights during learning of the K neural networks by K phoneme combination groups searched with the same neural networks, and composing an optimum-partitioned classified neural network combination using the K neural networks of which a total error sum has converged; and tuning a phoneme boundary of a first label file by using the phoneme combination group classification result and the optimum-partitioned classified neural network combination, and generating a final label file reflecting the tuning result.

REFERENCES:
patent: 5285522 (1994-02-01), Mueller
patent: 5461696 (1995-10-01), Frank et al.
patent: 5509103 (1996-04-01), Wang
patent: 5621857 (1997-04-01), Cole et al.
patent: 5621858 (1997-04-01), Stork et al.
patent: 5638487 (1997-06-01), Chigier
patent: 5668926 (1997-09-01), Karaali et al.
patent: 5737716 (1998-04-01), Bergstrom et al.
patent: 5749066 (1998-05-01), Nussbaum
patent: 5758023 (1998-05-01), Bordeaux
patent: 5963904 (1999-10-01), Lee et al.
patent: 6021387 (2000-02-01), Mozer et al.
patent: 6947890 (2005-09-01), Kitazoe et al.
Ananth Sankar, et al., “Growing and Pruning Neural Tree Networks”, IEEE Tranactions on Computers, vol. 42, No. 3, Mar. 1993, pp. 291-299.
Eun-Young Park, et al., “Automatic Speech Synthesis Unit Generation with MLP Based Postprocessor Against Auto-Segmented Phoneme Errors”, Dept. of Electronic Engr. Inha Univ. Inchon, Korea, Electronics and Telecommunication Research Institute, Korea © 1999 IEEE, pp. 2985-2988.
Doroteo Torre Toledano, “Neural Network Boundary Refining for Automatic Speech Segmentation”, Telefonica Investigacion y Desarrollo, Emilio Vargas 6, 28043—Madrid, Spain © 2000 IEEE, pp. 3438-3441.
Abhinav Sethy, et al., “Refined Speech Segmentation for Concatenative Speech Snythesis”, Speech Analysis and Interpretation Lab, Integrated Media Systems Center, Department of Electrical Engineering Systems, University of Southern California, XP-002370822.
Ki-Seung Lee, et al., “Context-Adaptive Phone Boundary Refining for a TTS Database”, Dept. of Electronic Eng. Konkuk University, 1 Hwayang-dong, Gwangju-gu, Seoul, Korea 143-701, © 2003 IEEE, pp. I-252-I-255.
European Search Report issued Mar. 30, 2006 for Application No. 04251145.1—2218.
D. T. Toledano, “Neural Network Boundary Refining for Automatic Speech Segmentation,” Proceedings of ICASSP-2000, pp. 3438-3441 (2000).
E. Y. Park et al., “Automatic Speech Synthesis Unit Generation with MLP based Postprocessor against Auto-segmented Phone Errors,” Proceedings of International Joint Conference on Neural Networks, pp. 2985-2990 (1999).

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

Method of setting optimum-partitioned classified neural... 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 of setting optimum-partitioned classified neural..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of setting optimum-partitioned classified neural... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-4017341

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