EM-based Gain Adaptation for Probabilistic Multipitch Tracking

TitleEM-based Gain Adaptation for Probabilistic Multipitch Tracking
Publication TypeConference Paper
Year of Publication2011
AuthorsWohlmayr, M., & Pernkopf F.
Conference NameInternational Conference on Spoken Language Processing (Interspeech)
Pages1969-1972
Conference LocationFlorence
Abstract

We introduce an EM algorithm for automatic speaker gain adap-
tation, and use this approach for probabilistic multipitch track-
ing. We derive a lower bound on the log-likelihood of the
gain parameters and use a fast pruning method to make lower
bound optimization efficient. We evaluate the performance of
gain adapted multipitch tracking on the GRID database, where
3000 speech mixtures were generated for each mixing level. For
gain differences in the range of zero up to 18dB, the proposed
method achieves almost the same performance as for the case
where the gain is assumed to be known.
 

Citation Key2104