Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses
HLT '91 Proceedings of the workshop on Speech and Natural Language
Statistical trajectory models for phonetic recognition
Statistical trajectory models for phonetic recognition
Parametric subspace modeling of speech transitions
Speech Communication
Markov processes on curves for automatic speech recognition
Proceedings of the 1998 conference on Advances in neural information processing systems II
Linear Dynamic Segmental HMMs: Variability Representation and Training Procedure
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Model Parameter Estimation for Mixture Density Polynomial Segment Models
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
A Diphone-Based Digit Recognition System Using Neural Networks
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 4 - Volume 4
Weight estimation for N-best rescoring
HLT '91 Proceedings of the workshop on Speech and Natural Language
Tree-based state tying for high accuracy acoustic modelling
HLT '94 Proceedings of the workshop on Human Language Technology
Temporal patterns (TRAPs) in ASR of noisy speech
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
The HDM: a segmental hidden dynamic model of coarticulation
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Initial evaluation of hidden dynamic models on conversational speech
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Unified frame and segment based models for automatic speech recognition
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Hi-index | 0.00 |
This paper describes an extension of the previously reported attempt of capturing segmental transition information for speech recognition tasks [Speech Communication 27 (1) (1999) 19]. Representations in the subspace with multiple projected trajectories are discussed, employing EM-based methods to find optimal anchor points. Experimental work is carried out to illustrate that useful discriminant information is preserved in the subspace trajectories. These experiments include the development of "matched filters" to spot particular diphones in continuous speech, and the inclusion of diphone-based discriminant information into a phone-based HMM recognition framework to rerank multiple hypotheses. The difficulties in constructing the models due to the limited coverage of a sufficient amount of tokens within the phone balanced TIMIT database are discussed. The influence of the restricted diphone coverage on the rescoring results is reported. Improvements in phone recognition accuracy have been obtained on a speaker-by-speaker basis. Obtained improvements over baseline HMMs augmented with first-order derivatives suggest the importance of explicitly modelled between-phone information.