GMM INCREMENTAL ROBUST ADAPTATION WITH FORGETTING FACTOR FOR SPEAKER VERIFICATION

摘要

Speaker recognition system uses a speaker model adaptation method with small amounts of data in order to obtain a good performance. However, in a conventional adaptation method, when new data has an outlier such as a noise or an utterance change, which results in inaccurate speaker model. As time goes by, a rate in which new data are adapted to a model is reduced. A new method uses an incremental robust adaptation in order to reduce effect of outlier and uses forgetting factor in order to maintain adaptive rate of new data.