Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Kaizhi Qian"'
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
A language-independent automatic speech recognizer (ASR) is one that can be used for phonetic transcription in languages other than the languages in which it was trained. Language-independent ASR is difficult to train, because different languages imp
Externí odkaz:
https://doaj.org/article/2cdf1e50351a408e81033dd1c0ba1fbd
Autor:
Junrui Ni, Liming Wang, Heting Gao, Kaizhi Qian, Yang Zhang, Shiyu Chang, Mark Hasegawa-Johnson
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f4d3ac80a6660337c93c5868d621dea
Publikováno v:
Frontiers in artificial intelligence. 5
A language-independent automatic speech recognizer (ASR) is one that can be used for phonetic transcription in languages other than the languages in which it was trained. Language-independent ASR is difficult to train, because different languages imp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab559744017c38285fb1fe70fe639e5b
https://pubmed.ncbi.nlm.nih.gov/35647534
https://pubmed.ncbi.nlm.nih.gov/35647534
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dc78865d60e84ee2ee7206ebc5fe519b
https://doi.org/10.21437/interspeech.2021-1843
https://doi.org/10.21437/interspeech.2021-1843
Publikováno v:
ICASSP
Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been proposed. Rece
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9672fe31466d62989992e2f77faa7dcb
https://doi.org/10.1109/icassp40776.2020.9054734
https://doi.org/10.1109/icassp40776.2020.9054734
Publikováno v:
APSIPA
Monaural singing voice separation has received much attention in recent years. In this paper, we propose a novel neural network architecture for monaural singing voice separation, Fusion-Net, which is combining U-Net with the residual convolutional n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7841078c330faf7318608e1b6b560ee4
https://doi.org/10.1109/apsipaasc47483.2019.9023055
https://doi.org/10.1109/apsipaasc47483.2019.9023055
Publikováno v:
Publons
Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial networks (GAN) and conditional variational autoencoder (CVAE), are being ap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfd3c4fb2c795dc730d691b45d9e8b06
Publikováno v:
ICASSP
Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would otherwise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a1acb6894ea714aa7e22217df070660
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c67b7f45d3bfe9402bed0e4766c1f0d
https://doi.org/10.21437/interspeech.2017-1672
https://doi.org/10.21437/interspeech.2017-1672
Publikováno v:
Speech Prosody 2016.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6e110383abca28e3d337cc33e29bc1e
https://doi.org/10.21437/speechprosody.2016-229
https://doi.org/10.21437/speechprosody.2016-229