Sparse representation features for speech recognition
Tara N. Sainath, Bhuvana Ramabhadran, et al.
INTERSPEECH 2010
A speaker adaptation strategy is described that is based on finding a subset of speakers, from the training set, who are acoustically close to the test speaker, and using only the data from these speakers (rather than the complete training corpus) to reestimate the system parameters. Further, a linear transformation is computed for every one of the selected training speakers to better map the training speaker's data to the test speaker's acoustic space. Finally, the system parameters (Gaussian means) are reestimated specifically for the test speaker using the transformed data from the selected training speakers. Experiments showed that this scheme is capable of providing an 18% relative improvement in the error rate on a large-vocabulary task with the use of as little as three sentences of adaptation data. © 1998 IEEE.
Tara N. Sainath, Bhuvana Ramabhadran, et al.
INTERSPEECH 2010
Xiaohui Shen, Gang Hua, et al.
FG 2011
R.A. Gopinath, Markus Lang, et al.
ICIP 1994
Vijay Arya, Diptikalyan Saha, et al.
CODS-COMAD 2023