Adapting acoustic models to new domains and conditions using untranscribed data
Asela Gunawardana, Alex Acero · 2003
This paper investigates the unsupervised adaptation of an acous-tic model to a domain with mismatched acoustic conditions. We use techniques borrowed from the unsupervised training litera-ture to adapt an acoustic model trained on the Wall Street Jour-nal corpus to the Aurora-2 domain, which is composed of read digit strings over a simulated noisy telephone channel. We show that it is possible to use untranscribed in-domain data to get sig-nificant performance improvements, even when it is severely mismatched to the acoustic model t 1.