Temporal patterns (TRAPs) in ASR of noisy speech

Authors:
H. Hermansky;S. Sharma
Affiliations:
Graduate Inst. of Sci. & Technol., Portland, OR, USA;-
Venue:
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Year:
1999

Citing 0
Cited 11

Diphone subspace mixture trajectory models for HMM Complementation

Speech Communication
Human Speech Perception: Some Lessons from Automatic Speech Recognition

TSD '01 Proceedings of the 4th International Conference on Text, Speech and Dialogue
Cepstral Statistics Compensation and Normalization Using Online Pseudo Stereo Codebooks for Robust Speech Recognition in Additive Noise Environments

IEICE - Transactions on Information and Systems
Unsupervised learning of time-frequency patches as a noise-robust representation of speech

Speech Communication
Hierarchical and parallel processing of auditory and modulation frequencies for automatic speech recognition

Speech Communication
Missing-feature reconstruction by leveraging temporal spectral correlation for robust speech recognition in background noise conditions

IEEE Transactions on Audio, Speech, and Language Processing
Robustness of spectro-temporal features against intrinsic and extrinsic variations in automatic speech recognition

Speech Communication
Acoustic modeling problem for automatic speech recognition system: conventional methods (Part I)

International Journal of Speech Technology
Acoustic modeling problem for automatic speech recognition system: advances and refinements (Part II)

International Journal of Speech Technology
Long-Term temporal features for conversational speech recognition

MLMI'04 Proceedings of the First international conference on Machine Learning for Multimodal Interaction
Exploiting deep neural networks for detection-based speech recognition

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study a new approach to processing temporal information for automatic speech recognition (ASR). Specifically, we study the use of rather long-time temporal patterns (TRAPs) of spectral energies in place of the conventional spectral patterns for ASR. The proposed neural TRAPs are found to yield significant amount of complementary information to that of the conventional spectral feature based ASR system. A combination of these two ASR systems is shown to result in improved robustness to several types of additive and convolutive environmental degradations.