For speech recognition, mismatches between training and testing for speaker and noise are normally handled separately. The work presented in this paper aims at jointly applying sp...
K. K. Chin, Haitian Xu, Mark J. F. Gales, Catherin...
Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can ...
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...
Many techniques for complex speech processing such as denoising and deconvolution, time/frequency warping, multiple speaker separation, and multiple microphone analysis operate on...
We describe an approach to simultaneous tokenization and part-of-speech tagging that is based on separating the closed and open-class items, and focusing on the likelihood of the ...