Recent research has shown that speech can be sparsely represented using a dictionary of speech segments spanning multiple frames, exemplars, and that such a sparse representation ...
Mismatch between training and test conditions deteriorates the performance of speech recognizers. This paper investigates the combination of parametric histogram equalization (pHE...
Missing data methods attempt to improve robust speech recognition by distinguishing between reliable and unreliable data in the time-frequency domain. Such methods require a binar...
In this paper, we propose a joint optimal method for automatic speech recognition (ASR) and ideal binary mask (IBM) estimation in transformed into the cepstral domain through a ne...
Lae-Hoon Kim, Kyung-Tae Kim, Mark Hasegawa-Johnson
In the `missing data' approach to improving the robustness of automatic speech recognition to added noise, an initial process identifies spectraltemporal regions which are do...