Continuous speech recognition using linked predictive neural networks

Authors:
J. Tebelskis;A. Waibel;B. Petek;O. Schmidbauer
Affiliations:
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA;Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA;Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA;Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Venue:
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Year:
1991

Citing 0
Cited 15

Robust ASR using Support Vector Machines

Speech Communication
Dynamic programming prediction errors of recurrent neural fuzzy networks for speech recognition

Expert Systems with Applications: An International Journal
Convergence comparison of LPC derived coefficients for speech pattern

ACST '08 Proceedings of the Fourth IASTED International Conference on Advances in Computer Science and Technology
SVMs for automatic speech recognition: a survey

Progress in nonlinear speech processing
PARSEC: a structured connectionist parsing system for spoken language

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Testing generality in JANUS: a multi-lingual speech translation system

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Context-dependent hidden control neutral network architecture for continuous speech recognition

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
An LVQ based reference model for speaker-adaptive speech recognition

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Hidden Markov models using vector linear prediction and discriminative output distributions

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
A discriminative neural prediction system for speech recognition

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
Performance through consistency: connectionist large vocabulary continuous speech recognition

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Exploiting prediction error in a predictive-based connectionist speech recognition system

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Efficient MLP constructive training algorithm using a neuron recruiting approach for isolated word recognition system

International Journal of Speech Technology
Predictive connectionist approach to speech recognition

Nonlinear Speech Modeling and Applications
A speech recognizer based on multiclass SVMs with HMM-Guided segmentation

NOLISP'05 Proceedings of the 3rd international conference on Non-Linear Analyses and Algorithms for Speech Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The authors present a large vocabulary, continuous speech recognition system based on linked predictive neural networks (LPNNs). The system uses neural networks as predictors of speech frames, yielding distortion measures which can be used by the one-stage DTW algorithm to perform continuous speech recognition. The system currently achieves 95%, 58%, and 39% word accuracy on tasks with perplexity 7, 111, and 402, respectively, outperforming several simple HMMs that have been tested. It was also found that the accuracy and speed of the LPNN can be slightly improved by the judicious use of hidden control inputs. The strengths and weaknesses of the predictive approach are discussed.