Improving Rapid Unsupervised Speaker Adaptation Based On Hmm Sufficient Statistics
Authors:
- R. GomezRGR. Gomez
- T. TodaTTT. Toda
- H. SaruwatariHSH. Saruwatari
- K. ShikanoKSK. Shikano
- 1 May 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149)
Abstract
In real-time speech recognition applications, there is a need to implement a fast and reliable adaptation algorithm. We propose a method to reduce adaptation time of the unsupervised speaker adaptation based on HMM-sufficient statistics. We use only a single arbitrary utterance without transcriptions in selecting the N-best speakers' sufficient statistics created offline to provide data for adaptation to a target speaker. Further reduction of N-best implies a reduction in adaptation time. However, it degrades recognition performance due to insufficiency of data needed to robustly adapt the model. Linear interpolation of the global HMM-sufficient statistics offsets this negative effect and achieves a 50% reduction in adaptation time without compromising the recognition performance. We have reduced the adaptation time from 10 sec to 5 sec without degradation of the word accuracy. Furthermore, we compared our method with vocal tract length normalization (VTLN), maximum a posteriori (MAP) and maximum likelihood linear regression (MLLR). Moreover, we tested in office, car, crowd and booth noise environments in 10 dB, 15 dB, 20 dB and 25 dB SNRsKeywords
This publication has 4 references indexed in Scilit:
- Improving Rapid Unsupervised Speaker Adaptation Based on HMM-Sufficient Statistics in Noisy Environments Using Multi-Template ModelsIEICE Transactions on Information and Systems, 2006
- Acoustic models of the elderly for large‐vocabulary continuous speech recognitionElectronics and Communications in Japan (Part II: Electronics), 2004
- Very fast adaptation with a compact context-dependent eigenvoice model2002
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995