Abstract
An approach for speaker adaptation aiming to get high recognition performance from an HMM speech recognizer after a short training session with a new speaker is presented. The technique presented exploits the Gaussian multivariate nature of continuous density HMM distributions, to adapt the model parameters. This adaptation technique was applied to a 20-word vocabulary. It was tested on 70 new speakers after a training session of 2 to 5 repetitions of each vocabulary word. The experiments carried out have shown a significant improvement in the recognition performance, even when only two training tokens from the new speaker are used.
Original language | English |
---|---|
Title of host publication | IEEE International Conference on Acoustics, Speech and Signal Processing 1991, ICASSP 91 |
Place of Publication | Toronto |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 861 - 864 |
Volume | vol.2 |
DOIs | |
Publication status | Published - 14 May 1991 |
Keywords
- hidden Markov models (HMMs)
- speech recognition
- HMM speech recogniser
- continuous densities HMMs