Skip to Main content Skip to Navigation
Conference papers

Exploring GMM-derived Features for Unsupervised Adaptation of Deep Neural Network Acoustic Models

Abstract : In this paper we investigate GMM-derived features recently introduced for adaptation of context-dependent deep neural network HMM (CD-DNN-HMM) acoustic models. We present an initial attempt of improving the previously proposed adaptation algorithm by applying lattice scores and by using con dence measures in the traditional max- imum a posteriori adaptation (MAP) adaptation algorithm. Modi ed MAP adaptation is performed for the auxiliary GMM model used in a speaker adaptation procedure for a DNN. In addition we introduce two approaches - data augmentation and data selection, for improving the regularization in MAP adaptation for DNN. Experimental results on the Wall Street Journal (WSJ0) corpus show that the proposed adaptation technique can provide, on average, up to 9:9% relative word error rate (WER) reduction under an unsupervised adaptation setup, compared to speaker independent DNN-HMM systems built on conventional features.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01433184
Contributor : Sylvain Meignier <>
Submitted on : Monday, November 19, 2018 - 9:35:10 AM
Last modification on : Thursday, November 29, 2018 - 11:18:42 AM
Document(s) archivé(s) le : Wednesday, February 20, 2019 - 1:13:47 PM

File

ExploringGMMDfeatures_SPECOM20...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01433184, version 1

Collections

Citation

Natalia Tomashenko, Yuri Khokhlov, Anthony Larcher, Yannick Estève. Exploring GMM-derived Features for Unsupervised Adaptation of Deep Neural Network Acoustic Models. 18th International Conference on Speech and Computer, 2016, Budapest, Hungary. ⟨hal-01433184⟩

Share

Metrics

Record views

176

Files downloads

175