Zobrazeno 1 - 10 of 28 pro vyhledávání: '"Nobukatsu Hojo"'
3
Many-to-Many Voice Transformer Network
Autor: Kou Tanaka, Nobukatsu Hojo, Takuhiro Kaneko, Hirokazu Kameoka, Tomoki Toda, Wen-Chin Huang
Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 29:656-670
This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech. We previously proposed an S2
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83195fb3a7b1dde82b57f7ebe5eb5f33
https://doi.org/10.1109/taslp.2020.3047262
Zobrazit plný text záznamu
5
Nonparallel Voice Conversion With Augmented Classifier Star Generative Adversarial Networks
Autor: Kou Tanaka, Takuhiro Kaneko, Hirokazu Kameoka, Nobukatsu Hojo
Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28:2982-2995
We previously proposed a method that allows for nonparallel voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of our method, called StarGAN-VC, are as follows: First, it requires no p
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::479c3568fdfff1406bf94ceda564d160
https://doi.org/10.1109/taslp.2020.3036784
Zobrazit plný text záznamu
6
Maskcyclegan-VC: Learning Non-Parallel Voice Conversion with Filling in Frames
Autor: Nobukatsu Hojo, Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka
Publikováno v: ICASSP
Non-parallel voice conversion (VC) is a technique for training voice converters without a parallel corpus. Cycle-consistent adversarial network-based VCs (CycleGAN-VC and CycleGAN-VC2) are widely accepted as benchmark methods. However, owing to their
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3bec03499e04bce7606eb498a2b199b
https://doi.org/10.1109/icassp39728.2021.9414851
Zobrazit plný text záznamu
7
ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder
Autor: Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Hirokazu Kameoka
Publikováno v: IEEE/ACM Transactions on Audio, Speech, and Language Processing. 27:1432-1443
This paper proposes a non-parallel voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE. The proposed method has two key features. First, it adopts fully convolutional archit
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b1b8eb8e1cf057466b63cc338eccfb79
https://doi.org/10.1109/taslp.2019.2917232
Zobrazit plný text záznamu
8
Model architectures to extrapolate emotional expressions in DNN-based text-to-speech
Autor: Katsuki Inoue, Yusuke Ijima, Masanobu Abe, Sunao Hara, Nobukatsu Hojo
This paper proposes architectures that facilitate the extrapolation of emotional expressions in deep neural network (DNN)-based text-to-speech (TTS). In this study, the meaning of "extrapolate emotional expressions" is to borrow emotional expressions
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67d77820eba73fb1ba2a9618255dab3b
Zobrazit plný text záznamu
9
CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-Spectrogram Conversion
Autor: Kou Tanaka, Nobukatsu Hojo, Takuhiro Kaneko, Hirokazu Kameoka
Publikováno v: INTERSPEECH
Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial network (CycleGAN)-VC and CycleGAN-VC2 have shown promising results reg
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0dd5ba6eee4fb8ff5d0993b41e1dec83
https://doi.org/10.21437/interspeech.2020-2280
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje