Despite years of speech recognition research, little is known about which words tend to be misrecognized and why. Previous work has shown that errors increase for infrequent words...
Sharon Goldwater, Daniel Jurafsky, Christopher D. ...
Improved acoustic modeling can significantly decrease the error rate in large-vocabulary speech recognition. Our approach to the problem is twofold. We first propose a scheme that...
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
9 A two-level mixture linear dynamic system model, with frame-level switching parameters in the obser10 vation equation and with segment-level switching parameters in the target-d...
Abstract. Opposing the pre-dominant turn-wise statistics of acoustic LowLevel-Descriptors followed by static classification we re-investigate dynamic modeling directly on the frame...