Current speech recognition systems are often based on HMMs with state-clustered Gaussian Mixture Models (GMMs) to represent the context dependent output distributions. Though high...
Abstract. In this paper we present early work on an animated talking head commentary system called Byrne. The goal of this project is to develop a system which can take the output ...
- Real-time speaker verification, with speech acquired using the NIST Mk-III microphone array and an autodirective beamforming algorithm, is demonstrated. The software and hardware...
Gang Mei, Roger Xu, Debang Lao, Chiman Kwan, Vince...
As more data becomes available for a given speech recognition task, the natural way to improve recognition accuracy is to train larger models. But, while this strategy yields mode...
We present in this paper methods to improve HMM-based part-of-speech (POS) tagging of Mandarin. We model the emission probability of an unknown word using all the characters in th...