Fast Speaker Adaptation Using Multi-stream Based Eigenvoice in Noisy Environments
In this paper, the multi-stream based eigenvoice method is proposed in order to overcome the weak points of conventional eigenvoice and dimensional eigenvoice methods in fast speaker adaptation. In the proposed method, multi-streams are automatically constructed by a method of the statistical clustering analysis that uses the information acquired by correlation between dimensions. To obtain the reliable distance matrix from the covariance matrix in order to divide full dimensions into the optimal number of streams, MAP adaptation technique is employed on the covariance matrix of training data and the sample covariance of adaptation data. According to vocabulary-independent word recognition experiment with several car noise levels and supervised adaptation mode, we obtained 29% and 31% relative improvements with 5 and 50 adaptation words at 20dB SNR in comparison with conventional eigenvoice, respectively. We also obtained 26% and 53% relative improvements with 5 and 50 adaptation words at 10dB SNR, respectively.
KeywordsNoisy Environment Adaptation Data Full Dimension Linkage Algorithm Adaptation Word
Unable to display preview. Download preview PDF.
- 4.Park, J.S., Song, H.J., Kim, H.S.: Performance improvement of rapid speaker adaptation based on eigenvoice and bias compensation. In: Proc. EuroSpeech, pp. 1481–1484 (2003)Google Scholar
- 5.Song, H.J., Kim, H.S.: Simultaneous Estimation of Weights of Eigenvoices and Bias Compensation Vector for Rapid Speaker Adaptation. In: Proc. ICSLP (2004)Google Scholar
- 6.Johnson, R.A., Wichern, D.W.: Applied Multivariate Statistical Analysis, 4th edn. Prentice-Hall, Englewood Cliffs (1998)Google Scholar
- 7.Lim, Y., Lee, Y.: Implementation of the POW (Phonetically Optimized Words) algorithm for speech database. In: Proc. ICASSP, vol. 1, pp. 89–91 (1995)Google Scholar
- 8.ITU recommendation P.56: Objective measurement of active speech level (1993)Google Scholar