[PDF][PDF] Applying voice conversion to concatenative singing-voice synthesis.
F Villavicencio, J Bonada - Interspeech, 2010 - isca-archive.org
This work address the application of Voice Conversion to singing-voice. The GMM-based
approach was applied to VOCALOID, a concatenative singing synthesizer, to perform singer …
approach was applied to VOCALOID, a concatenative singing synthesizer, to perform singer …
VocaListener and VocaWatcher: Imitating a human singer by using signal processing
In this paper, we describe three singing information processing systems, VocaListener,
VocaListener2, and VocaWatcher, that imitate singing expressions of the voice and face of a …
VocaListener2, and VocaWatcher, that imitate singing expressions of the voice and face of a …
Voice processing using conversion function based on respective statistics of a first and a second probability distribution
F Villavicencio - US Patent 9,343,060, 2016 - Google Patents
In Voice processing, a first distribution generation unit approximates a distribution of feature
information represen tative of voice of a first speaker per a unit interval thereof as a mixed …
information represen tative of voice of a first speaker per a unit interval thereof as a mixed …
Observation-model error compensation for enhanced spectral envelope transformation in voice conversion
F Villavicencio, J Bonada… - 2015 IEEE 25th …, 2015 - ieeexplore.ieee.org
A strategy to enhance the signal quality and naturalness was designed for performing
probabilistic spectral envelope transformation in voice conversion. The existing modeling …
probabilistic spectral envelope transformation in voice conversion. The existing modeling …
Applying spectral normalisation and efficient envelope estimation and statistical transformation for the voice conversion challenge 2016
F Villavicencio, J Yamagishi, J Bonada… - Interspeech 2016, 2016 - research.ed.ac.uk
In this work we present our entry for the Voice Conversion Challenge 2016, denoting new
features to previous work on GMM-based voice conversion. We incorporate frequency …
features to previous work on GMM-based voice conversion. We incorporate frequency …
VocaListener2: ユーザ歌唱の音高・音量に加えて声色変化も真似る歌声合成システム
中野倫靖， 後藤真孝 - 情報処理学会論文誌, 2013 - ipsj.ixsq.nii.ac.jp
論文抄録 本論文では, ユーザの歌声からその声色 (こわいろ) 変化を真似て歌声合成するシステム
VocaListener2 を提案する. 本システムは, 我々が以前開発した音高と音量のみを真似て歌声合成 …
VocaListener2 を提案する. 本システムは, 我々が以前開発した音高と音量のみを真似て歌声合成 …
人間の歌い方を真似る歌声合成システムVocaListener とロボット顔動作生成システムVocaWatcher (< 特集> 音楽制作と情報処理の友好関係)
後藤真孝， 中野倫靖， 梶田秀司， 松坂要佐… - システム/制御 …, 2012 - jstage.jst.go.jp
の 楽曲を多 くの 人 々 が積極的 に楽 しむ文化が成立する ことが, 世界で 初め て 実証されたの で
ある. しか し, 人間 らしい 自然 な歌声 を誰で も自在に合成可 能な技術は普及 してお らず …
ある. しか し, 人間 らしい 自然 な歌声 を誰で も自在に合成可 能な技術は普及 してお らず …