HMM speech synthesis based on MDCT representation
Sign Up to like & getrecommendations! Published in 2018 at "International Journal of Speech Technology"
DOI: 10.1007/s10772-018-09571-9
Abstract: Hidden Markov model (HMM) based text-to-speech (TTS) has become one of the most promising approaches, as it has proven to be a particularly flexible and robust framework to generate synthetic speech. However, several factors such… read more here.
Keywords: hmm speech; speech; mdct representation; speech synthesis ... See more keywords