Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Min-Jae Hwang"'
Publikováno v:
2022 International Conference on Electronics, Information, and Communication (ICEIC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abbb8fe784525bc3b1002e2487f90372
https://doi.org/10.1109/iceic54506.2022.9748515
https://doi.org/10.1109/iceic54506.2022.9748515
Publikováno v:
2022 International Conference on Electronics, Information, and Communication (ICEIC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0334e4ef44d7e5a262f4836aa6e6df11
https://doi.org/10.1109/iceic54506.2022.9748530
https://doi.org/10.1109/iceic54506.2022.9748530
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::130ef9383d1eef17e721cc4614bcc7b4
https://doi.org/10.21437/interspeech.2021-188
https://doi.org/10.21437/interspeech.2021-188
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16deffb09c888d2b23c81d63500604cb
https://doi.org/10.21437/interspeech.2021-976
https://doi.org/10.21437/interspeech.2021-976
Publikováno v:
ICASSP
This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's performance. Fur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cff6b569ea52cc21be23df427d8ae385
https://doi.org/10.1109/icassp39728.2021.9413369
https://doi.org/10.1109/icassp39728.2021.9413369
Publikováno v:
ICASSP
In this paper, we propose a text-to-speech (TTS)-driven data augmentation method for improving the quality of a non-autoregressive (AR) TTS system. Recently proposed non-AR models, such as FastSpeech 2, have successfully achieved fast speech synthesi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::867cb3922f4ca8e8c0e17fa067f5f51b
http://arxiv.org/abs/2010.13421
http://arxiv.org/abs/2010.13421
Publikováno v:
ICASSP
In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis systems by comb
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95fafdd73a792901939d26bd68afc12d
http://arxiv.org/abs/2001.11686
http://arxiv.org/abs/2001.11686
Publikováno v:
IEEE Transactions on Multimedia. 20:45-54
This paper proposes a blind digital audio water- marking algorithm that utilizes the quantization index modulation (QIM) and the singular value decomposition (SVD) of stereo audio signals. Conventional SVD-based blind audio watermarking algorithms la
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd48bdafb634d552fca69e1a822fc302
https://doi.org/10.1109/tmm.2017.2721642
https://doi.org/10.1109/tmm.2017.2721642
Autor:
Min-Jae Hwang, Hong-Goo Kang
Publikováno v:
INTERSPEECH
In this paper, we propose a deep learning (DL)-based parameter enhancement method for a mixed excitation linear prediction (MELP) speech codec in noisy communication environment. Unlike conventional speech enhancement modules that are designed to obt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9dec324c154a89ff4c65696316f969a1
https://doi.org/10.21437/interspeech.2019-3249
https://doi.org/10.21437/interspeech.2019-3249
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e42388f4a8a05ddb94690c9e86fa65f7
https://doi.org/10.21437/interspeech.2018-1590
https://doi.org/10.21437/interspeech.2018-1590