Method and apparatus for context-dependent estimation of multipl

Details Method and apparatus for context-dependent estimation of multipl Method and apparatus for context-dependent estimation of multipl

1992-06-22

1994-05-31

MacDonald, Allen R.

Electrical audio signal processing systems and devices

Hearing aids, electrical

Specified casing or housing

381 41, 381 42, G10L 506

Patent

active

053176731

ABSTRACT:
In a hidden Markov model-based speech recognition system, multilayer perceptrons (MLPs) are used in context-dependent estimation of a plurality of state-dependent observation probability distributions of phonetic classes. Estimation is obtained by the Bayesian factorization of the observation likelihood in terms of posterior probabilities of phone classes assuming the context and the input speech vector. The context-dependent estimation is employed as the state-dependent observation probabilities needed as parameter input to a hidden Markov model speech processor to identify the word sequence representing the unknown speech input of input speech vectors. Within the speech processor, models are provided which employ the observation probabilities in the recognition process. The number of context-dependent nets is reduced to a single net by sharing the units of the input layer and the hidden layer and the weights connecting them in the multilayer perceptron while providing one output layer for each relevant context. Each output layer is trained as an independent network on the specific examples of the corresponding context it represents. Training may be optimized at an intermediate set of weights between the context-independent-associated weights and the context-dependent associated weights to which training would normally converge.

REFERENCES:
patent: 5175793 (1992-12-01), Sakamoto et al.
patent: 5228087 (1993-07-01), Bickerton
Rabiner et al., "An Introduction to Hidden Markov Models," IEEE ASSP Magazine, Jan. 1986, pp. 4-16.
Richard P. Lippmann, entitled "An Introduction to Computing with Neural Nets," IEEE ASSP Magazine, Apr. 1987, pp. 4-23.
Paper entitled "Links between Markov Models and Multi-layer Perceptrons," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 12, pp. 1167-1178, Dec. 1990.
Bourlard et al., "CDNN: A Context Dependent Neural Network For Continuous Speech Recognition," Proc. of International Conference on Acoustics, Speech and Signal Processing 92, published Mar. 1992.

Affiliated with

Also associated with

Rating

Method and apparatus for context-dependent estimation of multipl 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 apparatus for context-dependent estimation of multipl, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for context-dependent estimation of multipl will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1634136