Method and system to scale down a decision tree-based hidden...

Details Method and system to scale down a decision tree-based hidden... Method and system to scale down a decision tree-based hidden...

2000-09-30

2008-12-30

Armstrong, Angela A (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

Reexamination Certificate

active

07472064

ABSTRACT:
A method and system are provided in which a decision tree-based model (“general model”) is scaled down (“trim-down”) for a given task. The trim-down model can be adapted for the given task using task specific data. The general model can be based on a hidden markov model (HMM). By allowing a decision tree-based acoustic model (“general model”) to be scaled according to the vocabulary of the given task, the general model can be configured dynamically into a trim-down model, which can be used to improve speech recognition performance and reduce system resource utilization. Furthermore, the trim-down model can be adapted/adjusted according to task specific data, e.g., task vocabulary, model size, or other like task specific data.

REFERENCES:
patent: 5684924 (1997-11-01), Stanley et al.
patent: 5899973 (1999-05-01), Bandara et al.
patent: 6324510 (2001-11-01), Waibel et al.
patent: WO-96/13830 (1996-05-01), None
Bub, Udo, “Task Adaptation for Dialogues Via Telephone Lines”,ICSLP, Fourth International Conference on Spoken Language Processing, (Oct. 6, 1996), 825-828.
Digalakis, Vassilios V., et al., “Speaker Adaptation Using Canstrained Estimation of Gaussian Mixtures”,IEEE Transactions on Speech and Audio Processing, vol. 3, No. 5, (Sep. 1995), Whole Document.
Digalakis, Vassilios V., et al., “Speaker Adaptation Using Combined Transformation and Bayesian Methods”,IEEE Transactions on Speech and Audio Processing, vol. 4, No. 4, (Jul. 1996), Whole Document.
Hon, Hsiao-Wuen, et al., “On Vocabulary-Independent Speech Modeling”,ICASSP 90 vol. 2, S2VA, Speech Processing 2, VLSI, Audio and Electroacoustics, International Conference on Acoustics, Speech, and Signal Processing, (Apr. 6, 1990), 725-728.
Hwang, Mei-Yuh, et al., “Dynamically Configurable Acoustics Models for Speech Recognition”,Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, vol. II of VI, Speech Processing II, Neural Networeks for SignalProcessing, (may 15, 1998), 669-672.

Affiliated with

Also associated with

Rating

Method and system to scale down a decision tree-based hidden... 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 and system to scale down a decision tree-based hidden..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system to scale down a decision tree-based hidden... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4047427