In spoken dialogue systems, it is important for a system to know how likely a speech recognition hypothesis is to be correct, so it can reprompt for fresh input, or, in cases wher...
Abstract. The present work is concerned with speech recognition using a small or medium size vocabulary. The possibility to use the English speech recognizer for the recognition of...
We present an implemented model for speech recognition in natural environments which relies on contextual information about salient entities to prime utterance recognition. The hyp...
— Missing feature theory (MFT) has demonstrated great potential for improving the noise robustness in speech recognition. MFT was mostly applied in the log-spectral domain since ...
This paper first introduces a newly-recorded high quality Romanian speech corpus designed for speech synthesis, called “RSS”, along with Romanian front-end text processing mo...
Adriana Stan, Junichi Yamagishi, Simon King, Matth...