Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jinhyeok Yang"'
There are two types of methods for non-autoregressive text-to-speech models to learn the one-to-many relationship between text and speech effectively. The first one is to use an advanced generative framework such as normalizing flow (NF). The second
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33f5aa637dbd5bf669da9148731e828c
Publikováno v:
Interspeech 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::641639d64faa8614f89e834d7c6d1ac0
https://doi.org/10.21437/interspeech.2022-737
https://doi.org/10.21437/interspeech.2022-737
Publikováno v:
KIISE Transactions on Computing Practices. 26:256-260
본 논문에서는 생성적 적대 신경망을 이용해 딥러닝 기반 TTS 모델이 합성한 멜 스펙트로그램을 실제 음성의 멜 스펙트로그램과 유사해지도록 개선하는 딥러닝 모델 TE-GAN(TTS Enhancement GAN)을
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80611d54dd13e3793703bff5bb0bcaca
https://doi.org/10.5626/ktcp.2020.26.5.256
https://doi.org/10.5626/ktcp.2020.26.5.256
Publikováno v:
International Journal on Document Analysis and Recognition (IJDAR). 22:407-416
We propose a large-scale Hangul font recognizer that is capable of recognizing 3300 Hangul fonts. Large-scale Hangul font recognition is a challenging task. Typically, Hangul fonts are distinguished by small differences in detailed shapes, which are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ad6d6bce696bf41ced9dbb2c07d7770
https://doi.org/10.1007/s10032-019-00337-w
https://doi.org/10.1007/s10032-019-00337-w
Recent advances in neural multi-speaker text-to-speech (TTS) models have enabled the generation of reasonably good speech quality with a single model and made it possible to synthesize the speech of a speaker with limited training data. Fine-tuning t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8097e6df725fc6199f99103bf091cd46
http://arxiv.org/abs/2106.15153
http://arxiv.org/abs/2106.15153
Publikováno v:
INTERSPEECH
We present a novel high-fidelity real-time neural vocoder called VocGAN. A recently developed GAN-based vocoder, MelGAN, produces speech waveforms in real-time. However, it often produces a waveform that is insufficient in quality or inconsistent wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e735b1ccb030ffcfd3b395aa82e6495c
https://doi.org/10.21437/interspeech.2020-1238
https://doi.org/10.21437/interspeech.2020-1238
Publikováno v:
Design, User Experience, and Usability: Novel User Experiences ISBN: 9783319403540
HCI (17)
HCI (17)
Emotion is one of the major factors for users to determine service preference. Especially online music streaming services are in trend-sensitive industry, hence largely affected by user’s experience and reputation. Conventional music streaming serv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c4489ddb662a5801d36f041746c7e7c
https://doi.org/10.1007/978-3-319-40355-7_11
https://doi.org/10.1007/978-3-319-40355-7_11