Discriminative feature extraction applied to speaker identification
J.H. Nealand, Alan B. Bradley, Margaret Lech · 2003
Speaker recognition systems typically consist of two individual modules providing feature extraction and classification. Conventional designs utilise a fixed feature extraction algorithm while a stochastic classifier is adapted during a training phase. Data-driven feature extraction involves adaptation of the feature extraction process in addition to the classifier during training. Discriminative feature extraction (DFE) is a data-driven feature extraction technique previously applied to speech recognition. This paper reports the application of DFE to the design of a filterbank for a Gaussian mixture model (GMM) based speaker identification system. The DFE trained filter-bank is shown to outperform conventional fixed filter-bank feature extraction.