24 citations · 69 across the 23 of their papers we have counts for
4 papers · 1 filter
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…
Neural Blind Source Separation and Diarization for Distant Speech Recognition
Yoshiaki Bando, Tomohiko Nakamura, Shinji Watanabe
This paper presents a neural method for distant speech recognition (DSR) that jointly separates and diarizes speech mixtures without supervision by isolated signals. A standard sep…
JaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
Tomohiko Nakamura, Shinnosuke Takamichi, Naoko Tanji +2
We construct a corpus of Japanese a cappella vocal ensembles (jaCappella corpus) for vocal ensemble separation and synthesis. It consists of 35 copyright-cleared vocal ensemble son…
Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders
Futa Nakashima, Tomohiko Nakamura, Norihiro Takamune +2
In this paper, we propose a musical instrument sound synthesis (MISS) method based on a variational autoencoder (VAE) that has a hierarchy-inducing latent space for timbre. VAE-bas…