Phoneme set clustering of accurate modeling is important in the task of multilingual speech recognition, especially when each of the available language training corpora is mismatc...
The present contribution aims at increasing our understanding of automatic speech recognition (ASR) errors involving frequent homophone or almost homophone words by confronting th...
In this paper we report our recent development of an end-to-end integrative design methodology for speech translation. Specifically, a novel decision function is proposed based o...
Due to upcoming mobile telephony services with higher speech quality, a wideband (50 Hz to 7 kHz) mobile telephony derivative of TIMIT has been recorded called WTIMIT. It allows a...
This paper addresses the problem of discriminative training of language models that does not require any transcribed acoustic data. We propose to minimize the conditional entropy ...