KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction
A user evaluation shows that the proposed KABURI-TTS attains higher naturalness at both the utterance and the interaction level, and an analysis of voice activity confirms that the proposed method produces more overlap and more frequent turn-taking.
Ryuichiro Higashinaka, Shinnosuke Takamichi, Tetsuji Ogawa
· 0 citations