We describe a novel technique for multi-sensory speech processing for enhancing noisy speech and for improved noiserobust speech recognition. Both air- and bone-conductive microph...
Amarnag Subramanya, Li Deng, Zicheng Liu, Zhengyou...
Current Automatic Speech Recognition (ASR) systems designed to recognize dysarthric speech require an investment in training that involves considerable effort and must be repeated ...
In this paper we revisit some basic configuration choices of HMMbased speech synthesis, such as waveform sampling rate, auditory frequency warping scale and the logarithmic scali...
Abstract. The use of high level information in source separation algorithms can greatly constrain the problem and lead to improved results by limiting the solution space to semanti...
Prior models of speech have been used in robust automatic speech recognition to enhance noisy speech. Typically, a single prior model is trained by pooling the entire training dat...
Arun Narayanan, Xiaojia Zhao, DeLiang Wang, Eric F...