Sixth International Conference on Spoken Language Processing
This paper deals with two questions. First, starting from the WSJ-trained recognizer, how much adaptation data (taken from the Phonebook training corpus) is necessary to achieve a reasonable recognition performance in spite of the high degree of mismatch? Second, is it possible to improve the recognition performance of a Phonebook-trained baseline acoustic model by using additional out-of-domain training data? The paper describes the adaptation and normalization techniques used to bridge the mismatch between the two corpora.
Bibliographic reference. Blasig, Reinhard / Rose, Georg / Meyer, Carsten (2000): "Training of isolated word recognizers with continuous speech", In ICSLP-2000, vol.1, 449-452.