Zobrazeno 1 - 10
of 37
pro vyhledávání: '"David Haws"'
Publikováno v:
International Journal of Distributed Sensor Networks, Vol 9 (2013)
While the theoretical foundation of the optimal camera placement problem has been studied for decades, its practical implementation has recently attracted significant research interest due to the increasing popularity of visual sensor networks. The m
Externí odkaz:
https://doaj.org/article/0d50f39fbc48416b946df122b66d8e0c
Sequence-to-Sequence Text-to-Speech architectures that directly generate low level acoustic features from phonetic sequences are known to produce natural and expressive speech when provided with adequate amounts of training data. Such systems can lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9b5070089b06e24f85f0fc0cddec9a6a
http://arxiv.org/abs/2207.12262
http://arxiv.org/abs/2207.12262
Beam search, which is the dominant ASR decoding algorithm for end-to-end models, generates tree-structured hypotheses. However, recent studies have shown that decoding with hypothesis merging can achieve a more efficient search with comparable or bet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5508e842bdd7f079e8bc6b494339d37
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fec0a2676550ca73ff5707b4d9228d09
https://doi.org/10.21437/interspeech.2021-1656
https://doi.org/10.21437/interspeech.2021-1656
When recurrent neural network transducers (RNNTs) are trained using the typical maximum likelihood criterion, the prediction network is trained only on ground truth label sequences. This leads to a mismatch during inference, known as exposure bias, w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::43552ddc9234b56d1b9945330f610fea
http://arxiv.org/abs/2108.10803
http://arxiv.org/abs/2108.10803
Publikováno v:
ICASSP
Autoregressive Attentive Sequence-to-Sequence (S2S) speech synthesis is considered state-of-the-art in terms of speech quality and naturalness, as evaluated on a finite set of testing utterances. However, it can occasionally suffer from stability iss
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e100512107ef39ee55ea5043f7cdaa69
https://doi.org/10.1109/icassp39728.2021.9414402
https://doi.org/10.1109/icassp39728.2021.9414402
Publikováno v:
SLT
Although Sequence-to-Sequence (S2S) architectures have become state-of-the-art in speech synthesis, capable of generating outputs that approach the perceptual quality of natural samples, they are limited by a lack of flexibility when it comes to cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f7e4a7a83c0d7377009900a3d3b3598
http://arxiv.org/abs/2101.09940
http://arxiv.org/abs/2101.09940
Autor:
David Haws
Publikováno v:
2004 Annual Conference Proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb58ebfe6101a0ea686e8029ffa27b38
https://doi.org/10.18260/1-2--13764
https://doi.org/10.18260/1-2--13764
Autor:
David Haws
Publikováno v:
2002 Annual Conference Proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3845193a0865321417b9083cb74a1f85
https://doi.org/10.18260/1-2--10687
https://doi.org/10.18260/1-2--10687
Autor:
David Haws
Publikováno v:
2006 Annual Conference & Exposition Proceedings.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d8085141adee3b06bbfab61b84693f2e
https://doi.org/10.18260/1-2--26
https://doi.org/10.18260/1-2--26