Journal ArticleDOI
Mean and variance adaptation within the MLLR framework
TLDR
This paper examines the maximum likelihood linear regression (MLLR) adaptation technique, which has been applied to the mean parameters in mixture-Gaussian HMM systems and is extended to also update the Gaussian variances and re-estimation formulae are derived for these variance transforms.About:
This article is published in Computer Speech & Language.The article was published on 1996-10-01. It has received 469 citations till now.read more
Citations
More filters
Proceedings ArticleDOI
Librispeech: An ASR corpus based on public domain audio books
TL;DR: It is shown that acoustic models trained on LibriSpeech give lower error rate on the Wall Street Journal (WSJ) test sets than models training on WSJ itself.
Journal ArticleDOI
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
TL;DR: A pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output that can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs.
Journal ArticleDOI
Maximum likelihood linear transformations for HMM-based speech recognition
TL;DR: The paper compares the two possible forms of model-based transforms: unconstrained, where any combination of mean and variance transform may be used, and constrained, which requires the variance transform to have the same form as the mean transform.
Journal ArticleDOI
Semi-tied covariance matrices for hidden Markov models
TL;DR: A new form of covariance matrix which allows a few "full" covariance matrices to be shared over many distributions, whilst each distribution maintains its own "diagonal" covariancy matrix is introduced.
Journal ArticleDOI
Rapid speaker adaptation in eigenvoice space
TL;DR: A new model-based speaker adaptation algorithm called the eigenvoice approach, which constrains the adapted model to be a linear combination of a small number of basis vectors obtained offline from a set of reference speakers, and thus greatly reduces the number of free parameters to be estimated from adaptation data.
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Journal ArticleDOI
Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
Jean-Luc Gauvain,Chin-Hui Lee +1 more
TL;DR: A framework for maximum a posteriori (MAP) estimation of hidden Markov models (HMM) is presented, and Bayesian learning is shown to serve as a unified approach for a wide range of speech recognition applications.
Proceedings ArticleDOI
Tree-based state tying for high accuracy acoustic modelling
TL;DR: This paper describes a method of creating a tied-state continuous speech recognition system using a phonetic decision tree, which is shown to lead to similar recognition performance to that obtained using an earlier data-driven approach but to have the additional advantage of providing a mapping for unseen triphones.
Proceedings ArticleDOI
Hidden Markov model decomposition of speech and noise
Andrew Varga,Roger K. Moore +1 more
TL;DR: A technique of signal decomposition using hidden Markov models is described that provides an optimal method of decomposing simultaneous processes and has wide implications for signal separation in general and improved speech modeling in particular.
Journal ArticleDOI
Speaker adaptation using constrained estimation of Gaussian mixtures
TL;DR: A constrained estimation technique for Gaussian mixture densities for speech recognition that approaches the speaker-independent accuracy achieved for native speakers and speaker-dependent systems that use six times as much training data.
Related Papers (5)
Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
Jean-Luc Gauvain,Chin-Hui Lee +1 more