In this paper we present a study of automatic speech recognition systems using context-dependent phonemes and graphemes as sub-word units based on the conventional HMM/GMM system a...
Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detect...
This paper provides an analysis of the impacts of machine translation and speech synthesis on speech-to-speech translation systems. The speech-to-speech translation system consist...
Kei Hashimoto, Junichi Yamagishi, William J. Byrne...
The concept of speaker recognition using i-vectors was recently introduced offering state-of-the-art performance. An i-vector is a compact representation of a speaker’s utteranc...
This paper presents a method for rescoring the speech recognition lattices on-the-fly to increase the word accuracy while preserving low latency of a real-time speech recognition ...