Abstract. Natural speech is produced by the vocal organs of a particular talker. The acoustic features of the speech signal must therefore be correlated with the movements of the a...
We propose a new approach for combining acoustic and visual measurements to aid in recognizing lip shapes of a person speaking. Our method relies on computing the maximum likeliho...
A conventional automatic speech recognizer does not perform well in the presence of noise, while human listeners are able to segregate and recognize speech in noisy conditions. We...
Yang Shao, Zhaozhang Jin, DeLiang Wang, Soundarara...
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we e...
Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hyn...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. We present a framework to ...