Recently adaptive training schemes using model based compensation approaches such as VTS and JUD have been proposed. Adaptive training allows the use of multi-environment training data whilst training a neutral, “clean”, acoustic model to be trained. This paper describes and assesses the advantages of using incremental, rather than batch, mode adaptation with these adaptively trained systems. Incremental adaptation reduces the latency during recognition, and has the possibility of reducing the error rate for slowly varying noise. The work is evaluated on a large scale multi-environment training configuration targeted at in-car speech recognition. Results on in-car collected test data indicate that incremental adaptation is an attractive option when using these adaptively trained systems.
Bibliographic reference. Flego, F. / Gales, M. J. F. (2009): "Incremental adaptation with VTS and joint adaptively trained systems", In INTERSPEECH-2009, 1251-1254.