Metraipolis › archive › dc_bf57f66efadf

KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction — arXiv:2609.07200

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07200
License (as archived)
CC0-1.0
Archived
2026-10-16T12:57:11.659Z
SHA-256 of the archived text
f5bfae955d4298216be86751cf278b92e61655ebe48acf811a2b6f556b97bca4
Stable URL of this page
https://metraipolis.com/documento/dc_bf57f66efadf

How to cite

KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction — arXiv:2609.07200 — arXiv (en), https://arxiv.org/abs/2609.07200 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf57f66efadf (Metraipolis archive dc_bf57f66efadf, sha256 f5bfae955d4298216be86751cf278b92e61655ebe48acf811a2b6f556b97bca4)
BibTeX
@misc{dcbf57f66efadf,
  title = {KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction — arXiv:2609.07200},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07200},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf57f66efadf; sha256 f5bfae955d4298216be86751cf278b92e61655ebe48acf811a2b6f556b97bca4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07200. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Realizing full-duplex spoken dialogue requires large amounts of two-channel, one-speaker-per-channel conversational speech data. Although conversational text-to-speech (TTS) engines have been developed, they are not necessarily robust to two-party simultaneous phenomena such as backchannels, interruptions, and overlaps that occur while the interlocutor is speaking. In this work, aiming at conversational speech synthesis that reproduces human-like overlap, we propose KABURI-TTS. KABURI-TTS takes a per-speaker phoneme raster as input and renders the speech of the two speakers on separate channels, conditioned on the per-frame phonemes and the voice activity derived from them. Because the phoneme raster is supplied by a separate module, the proposed method enables controllable generation of one-speaker-per-channel, two-party spoken dialogue. A user evaluation shows that, compared with strong baselines, the proposed method attains higher naturalness at both the utterance and the interaction level. Furthermore, an analysis of voice activity confirms that the proposed method produces more overlap and more frequent turn-taking.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.07200 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T12:30:25.306Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).