Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Ahmed Hussen Abdelaziz"'
Autor:
Yannis Stylianou, Chloe Seivwright, Anushree Prasanna Kumar, Gabriele Fanelli, Sachin Kajareker, Justin G. Binder, Ahmed Hussen Abdelaziz
Publikováno v:
ICMI
Audiovisual speech synthesis is the problem of synthesizing a talking face while maximizing the coherency of the acoustic and visual speech. In this paper, we propose and compare two audiovisual speech synthesis systems for 3D face models. The first
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6aaaa8b48908015f0df33129c25d56e3
https://doi.org/10.1145/3462244.3479883
https://doi.org/10.1145/3462244.3479883
Autor:
Ahmed Hussen Abdelaziz
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 26:475-484
Audiovisual fusion is one of the most challenging tasks that continues to attract substantial research interest in the field of audiovisual automatic speech recognition (AV-ASR). In the last few decades, many approaches for integrating the audio and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13fbe9e5c139f4a8f15d079a9e2ece9f
https://doi.org/10.1109/taslp.2017.2783545
https://doi.org/10.1109/taslp.2017.2783545
Autor:
Zakaria Aldeneh, Ahmed Hussen Abdelaziz, Devang Naik, Erik Marchi, Barry-John Theobald, Anushree Prasanna Kumar, Sachin S. Kajarekar
Publikováno v:
ICASSP
We present an introspection of an audiovisual speech enhancement model. In particular, we focus on interpreting how a neural audiovisual speech enhancement model uses visual cues to improve the quality of the target speech signal. We show that visual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::363bfbf343bf136a979b620c28c30afb
Autor:
Reinhard Knothe, Ahmed Hussen Abdelaziz, Paul R. Dixon, Sachin Kajareker, Barry-John Theobald, Nicholas Apostoloff
Publikováno v:
ICMI
We describe our novel deep learning approach for driving animated faces using both acoustic and visual information. In particular, speech-related facial movements are generated using audiovisual information, and non-speech facial movements are genera
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d67fff2efd9a0040c35647cbbc38ebfa
Autor:
Ahmed Hussen Abdelaziz, Sachin Kajareker, Nicholas Apostoloff, Barry-John Theobald, Justin G. Binder, Gabriele Fanelli, Thibaut Weise, Paul R. Dixon
Publikováno v:
ICMI
Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNN
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1616cba3688ea185530f249d300e81f4
https://doi.org/10.1145/3340555.3353745
https://doi.org/10.1145/3340555.3353745
Publikováno v:
Speech Communication. 79:1-13
Uncertainty decoding has recently been successful in improving automatic speech recognition performance in noisy environments by considering the pre-processed feature vectors not as deterministic but rather as random variables containing estimation e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d7c4610fd41a221e0e712162376a5d2
https://doi.org/10.1016/j.specom.2016.02.002
https://doi.org/10.1016/j.specom.2016.02.002
Autor:
Ahmed Hussen Abdelaziz
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a1035b403f58f41c95f9517139a6f140
https://doi.org/10.21437/interspeech.2017-860
https://doi.org/10.21437/interspeech.2017-860
Autor:
Ahmed Hussen Abdelaziz
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd9912efbeb0761740efed7b54a6f9f0
https://doi.org/10.21437/interspeech.2017-799
https://doi.org/10.21437/interspeech.2017-799
Autor:
Ahmed Hussen Abdelaziz
Publikováno v:
ICME
Reliable visual features that encode the articulator movements of speakers can dramatically improve the decoding accuracy of automatic speech recognition systems when combined with the corresponding acoustic signals. In this paper, a novel framework
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40d7180d43529bc6763a06929e16ac9d
https://doi.org/10.1109/icme.2017.8019294
https://doi.org/10.1109/icme.2017.8019294
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc811c6fd323576dc52e1464dabb8d50
https://doi.org/10.21437/interspeech.2016-166
https://doi.org/10.21437/interspeech.2016-166