Using child directed speech to bootstrap a model based...

Details Using child directed speech to bootstrap a model based... Using child directed speech to bootstrap a model based...

2007-09-21

2011-11-29

Sked, Matthew (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S243000, C704S253000, C704S254000

Reexamination Certificate

active

08069042

ABSTRACT:
A method and system for obtaining a pool of speech syllable models. The model pool is generated by first detecting a training segment using unsupervised speech segmentation or speech unit spotting. If the model pool is empty, a first speech syllable model is trained and added to the model pool. If the model pool is not empty, an existing model is determined from the model pool that best matches the training segment. Then the existing module is scored for the training segment. If the score is less than a predefined threshold, a new model for the training segment is created and added to the pool. If the score equals the threshold or is larger than the threshold, the training segment is used to improve or to re-estimate the model.

REFERENCES:
patent: 5659662 (1997-08-01), Wilcox et al.
patent: 6272463 (2001-08-01), Lapere
patent: 6912499 (2005-06-01), Sabourin et al.
patent: 7216079 (2007-05-01), Barnard et al.
patent: 7472066 (2008-12-01), Kuo et al.
patent: 7533019 (2009-05-01), Hakkani-Tur et al.
Collat, A. et al. “Unsupervised bootstrapping of diphone-like templates for connected speech recognition,” Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '87.
Nakagawa, S. et al. “A method for continuous speech segmentation using HMM,” Pattern Recognition, 1988., 9th International Conference on.
Wessel, F. et al. “Unsupervised training of acoustic models for large vocabulary continuous speech recognition,” Speech and Audio Processing, IEEE Transactions on, Issue Date: Jan. 2005.
European Search Report, EP 06020644, Dec. 19, 2006, 10 pages.
Maokuan, L. et al., “Unlabeled Data Classification Via Support Vector Machines and k-means Clustering,” Proceedings of the International Conference on Computer Graphics, Imaging and Visualization, CGIV 2004, Proceedings, Jul. 26-29, 2004, pp. 183-186.
Murthy, H.A. et al., “Automatic Segmentation and Labeling of Continuous Speech Without Bootstrapping,” EUSIPCO, Poster-presentation, 2004, [online] [Retrieved on Dec. 1, 2006] Retrieved from the Internet<URL:http://lantana.tenet.res.in/Publications/Speech/eusipco.pdf>.
Pham, T., “Alignment-Free Sequence Comparison with Vector Quantization and Hidden Markov Models,” Proceedings of the 2003 IEEE Bioinformatics Conference, CSB 2003, Aug. 11, 2003, pp. 534-535.
Salvi, G., “Ecological Language Acquisition Via Incremental Model-Based Clustering,” Interspeech 2005, Sep. 4-8, 2005, Lisbon, Portugal, pp. 1181-1184.
Sarada, G.L. et al., “Automatic Transcription of Continuous Speech Using Unsupervised and Incremental Training,” Poster-Presentation, InterSpeech 2004, 17 pages.

Affiliated with

Also associated with

Rating

Using child directed speech to bootstrap a model based... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Using child directed speech to bootstrap a model based..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Using child directed speech to bootstrap a model based... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4271036