3 accepted papers
Speaker verification technology has been successfully adopted and integrated into many applications. However, most of these applications require a microphone located near the talker. For the case of distant microphones, speech signals are corrupted by reverberations caused by the large speaker to mi…
In this paper, a feature set referred to as Discrete Cosine Series (DCS) is proposed for noise robust Automatic Speech Recognition (ASR). Unlike many other robust algorithms which use various forms of “long term” processing, DCS uses a small frame spacing to facilitate separating speech from noise a…
For many years, filterbank have been widely used as one step of frontend feature extraction for Automatic Speech Recognition (ASR). In this paper, we propose a unified framework for ASR frontends, by first moving the nonlinear amplitude scaling, and then combining the filterbank weights with the cos…