On combining i-vectors and discriminative adaptation methods for unsupervised speaker normalization in DNN acoustic models
Authors:
- 1 March 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5275-5279
Abstract
In automatic speech recognition (ASR), adaptation and adaptive training techniques are used to perform speaker normalization. Previous methods mainly focus on using these techniques in isolation. In contrast, this paper investigates two approaches to improve the ASR performance by combining i-vector based speaker adaptive training in deep neural network (DNN) acoustic models with discriminative adaptation techniques. First, we combine these techniques by interpolating the decoding lattices of i-vector based systems with the decoding lattices of a discriminatively adapted model. Then, we combine these methods by discriminatively adapting the i-vector based system in unsupervised fashion. Our experiments on TED-LIUM dataset show that compared with a strong speaker independent baseline, lattice interpolation and adaptation of the i-vector systems achieve 12.0% and 15.6% relative improvements, respectively. Moreover, in comparison to the i-vector based systems, lattice interpolation reported a 4.5% relative improvement while discriminatively adapting the i-vector system reported a 8.3% relative improvement.Keywords
This publication has 22 references indexed in Scilit:
- Scaling recurrent neural network language models2015
- Differentiable pooling for unsupervised speaker adaptation2015
- Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models2014
- Improving DNN speaker independence with I-vector inputs2014
- Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code2013
- Adaptation of context-dependent deep neural networks for automatic speech recognition2012
- Generating exact lattices in the WFST framework2012
- Two-Stage Speaker Adaptation of Hybrid Tied-Posterior Acoustic Models2006
- Adaptation of Hybrid ANN/HMM Models Using Linear Hidden Transformations and Conservative Training2006
- Tandem connectionist feature extraction for conventional HMM systems2002