Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Yukiya Hono"'
Publikováno v:
IEEE Access, Vol 9, Pp 137599-137612 (2021)
This paper presents PeriodNet, a non-autoregressive (non-AR) waveform generative model with a new model structure for modeling periodic and aperiodic components in speech waveforms. Non-AR raw waveform generative models have enabled the fast generati
Externí odkaz:
https://doaj.org/article/679dc822cf05493fbbd5e72bb4af426f
Publikováno v:
IEEE Access, Vol 9, Pp 137599-137612 (2021)
This paper presents PeriodNet, a non-autoregressive (non-AR) waveform generative model with a new model structure for modeling periodic and aperiodic components in speech waveforms. Non-AR raw waveform generative models have enabled the fast generati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c8f7f32f7b6eeaa375cbdf24044a8cb
https://ieeexplore.ieee.org/document/9559963/
https://ieeexplore.ieee.org/document/9559963/
This paper presents Sinsy, a deep neural network (DNN)-based singing voice synthesis (SVS) system. In recent years, DNNs have been utilized in statistical parametric SVS systems, and DNN-based SVS systems have demonstrated better performance than con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2316803387cb41958390ec501bd7d423
http://arxiv.org/abs/2108.02776
http://arxiv.org/abs/2108.02776
Publikováno v:
ICASSP
We propose PeriodNet, a non-autoregressive (non-AR) waveform generation model with a new model structure for modeling periodic and aperiodic components in speech waveforms. The non-AR waveform generation models can generate speech waveforms parallell
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::452d0385a2bdd0655d99ed2bd76505a3
Autor:
Kei Hashimoto, Keiichiro Oura, Yukiya Hono, Kei Sawada, Yoshihiko Nankaku, Kazuna Tsuboi, Keiichi Tokuda
Publikováno v:
INTERSPEECH
This paper proposes a hierarchical generative model with a multi-grained latent variable to synthesize expressive speech. In recent years, fine-grained latent variables are introduced into the text-to-speech synthesis that enable the fine control of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10bb590bce312e907f94103aaf76d904
http://arxiv.org/abs/2009.08474
http://arxiv.org/abs/2009.08474
Autor:
Yoshihiko Nankaku, Keiichiro Oura, Yukiya Hono, Kei Sawada, Keiichi Tokuda, Kei Hashimoto, Koki Senda
Publikováno v:
APSIPA
This paper proposes a method of selecting training data for many-to-one singing voice conversion (VC) from waveform data on the social media music app “nana.” On this social media app, users can share sounds such as speaking, singing, and instrum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc77f67e35698a0acf7a562614428a30
https://doi.org/10.23919/apsipa.2018.8659568
https://doi.org/10.23919/apsipa.2018.8659568
Autor:
Yoshihiko Nankaku, Keiichiro Oura, Kazuhiro Nakamura, Shumma Murata, Kei Hashimoto, Yukiya Hono, Keiichi Tokuda
Publikováno v:
APSIPA
This paper describes a singing voice synthesis system based on deep neural networks (DNNs) named Sinsy. Singing voice synthesis systems based on hidden Markov models (HMMs) have grown in the last decade. Recently, singing voice synthesis systems base
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1aa01c18fa9537fcb58b690d60158d9c
https://doi.org/10.23919/apsipa.2018.8659797
https://doi.org/10.23919/apsipa.2018.8659797