Open AccessProceedings Article
TRAPS - classifiers of temporal patterns.
Hynek Hermansky,Sangita Sharma +1 more
Reads0
Chats0
TLDR
The work proposes a radically different set of features for ASR where TempoRAl Patterns of spectral energies are used in place of the conventional spectral patterns.Abstract:
The work proposes a radically di erent set of features for ASR where TempoRAl Patterns of spectral energies are used in place of the conventional spectral patterns The approach has several inherent advantages, among them robustness to stationary or slowly varying disturbancesread more
Citations
More filters
Journal ArticleDOI
Acoustic Modeling Using Deep Belief Networks
TL;DR: It is shown that better phone recognition on the TIMIT dataset can be achieved by replacing Gaussian mixture models by deep neural networks that contain many layers of features and a very large number of parameters.
Journal ArticleDOI
An overview of noise-robust automatic speech recognition
TL;DR: A thorough overview of modern noise-robust techniques for ASR developed over the past 30 years is provided and methods that are proven to be successful and that are likely to sustain or expand their future applicability are emphasized.
Journal ArticleDOI
Automatic speech recognition and speech variability: A review
Mohamed Faouzi BenZeghiba,R. De Mori,Olivier Deroo,Stéphane Dupont,T. Erbes,D. Jouvet,Luciano Fissore,Pietro Laface,Alfred Mertins,Christophe Ris,Richard Rose,Vivek Tyagi,Christian Wellekens +12 more
TL;DR: Current advances related to automatic speech recognition (ASR) and spoken language systems and deficiencies in dealing with variation naturally present in speech are outlined.
Proceedings ArticleDOI
Probabilistic and Bottle-Neck Features for LVCSR of Meetings
TL;DR: This work is exploring the possibility of obtaining the features directly from neural net without the necessity of converting output probabilities to features suitable for subsequent GMM-HMM system.
Proceedings Article
Improved Bottleneck Features Using Pretrained Deep Neural Networks.
Dong Yu,Michael L. Seltzer +1 more
TL;DR: This paper shows how the use of unsupervised pretraining of a DNN enhances the network’s discriminative power and improves the bottleneck features it generates, and shows that a neural networktrained to predict context-dependent senone targets produces better bottleneck features than one trained to predict monophone states.
References
More filters
Journal ArticleDOI
Perceptual linear predictive (PLP) analysis of speech
TL;DR: A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, which uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum, and yields a low-dimensional representation of speech.
Book
Connectionist Speech Recognition: A Hybrid Approach
Hervé Bourlard,Nelson Morgan +1 more
TL;DR: Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state-of-the-art continuous speech recognition systems based on Hidden Markov Models (HMMs) to improve their performance.
Journal ArticleDOI
How do humans process and recognize speech
TL;DR: Until the performance of automatic speech recognition (ASR) hardware surpasses human performance in accuracy and robustness, the authors stand to gain by understanding the basic principles behind human Speech recognition (HSR).
Proceedings ArticleDOI
A mew ASR approach based on independent processing and recombination of partial frequency bands
Hervé Bourlard,Stéphane Dupont +1 more
TL;DR: The preliminary results presented in this paper show that such an approach, even using quite simple recombination strategies, can yield at least comparable performance on clean speech while providing better robustness in the case of noisy speech.