9 papers
J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling
Wataru Nakata, Kentaro Seki, Hitomi Yanaka +3
Spoken dialogue is essential for human-AI interactions, providing expressive capabilities beyond text. Developing effective spoken dialogue systems (SDSs) requires large-scale, hig…
DNN-based ensemble singing voice synthesis with interactions between singers
Hiroaki Hyodo, Shinnosuke Takamichi, Tomohiko Nakamura +2
We propose a singing voice synthesis (SVS) method for a more unified ensemble singing voice by modeling interactions between singers. Most existing SVS methods aim to synthesize a…
BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec
Detai Xin, Xu Tan, Shinnosuke Takamichi +1
We present BigCodec, a low-bitrate neural speech codec. While recent neural speech codecs have shown impressive progress, their performance significantly deteriorates at low bitrat…
SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics
Takaaki Saeki, Soumi Maiti, Shinnosuke Takamichi +2
While subjective assessments have been the gold standard for evaluating speech generation, there is a growing need for objective metrics that are highly correlated with human subje…
SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis
Osamu Take, Shinnosuke Takamichi, Kentaro Seki +2
This paper presents SaSLaW, a spontaneous dialogue speech corpus containing synchronous recordings of what speakers speak, listen to, and watch. Humans consider the diverse environ…
Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals
Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune +3
This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice…