Speech-rate-variable Hmm-based Japanese Tts System

@inproceedings{Iwano2002SpeechratevariableHJ,
  title={Speech-rate-variable Hmm-based Japanese Tts System},
  author={Koji Iwano and Masahiro Yamada and Taro Togawa and Sadaoki Furui},
  year={2002}
}
This paper proposes a new method for controlling phoneme duration according to arbitrary target speech rate in speech synthesis (TTS, text-to-speech) systems. The proposed method first constructs three fundamental duration models at “fast”, “normal”, and “slow” speech rates using Hayashi’s Quantification Theory (Type 1) based on real speech databases and creates a duration model according to a target speech rate by interpolating the fundamental models. Our TTS system uses an HMM-based… CONTINUE READING