E-LIB Suche - Ergebnisse für: Hussen Abdelaziz, Ahmed

1

Audiovisual Speech Synthesis using Tacotron2:

, In: Proceedings of the 2021 International Conference on Multimodal Interaction,

Hussen Abdelaziz, Ahmed ; Kumar, Anushree Prasanna ; Seivwright, Chloe... - p. 503-511 , 2021

Link: https://dl.acm.org/doi/1..

2

Modality Dropout for Improved Performance-driven Talking Fa..:

, In: Proceedings of the 2020 International Conference on Multimodal Interaction,

Hussen Abdelaziz, Ahmed ; Theobald, Barry-John ; Dixon, Paul... - p. 378-386 , 2020

Link: https://dl.acm.org/doi/1..

3

Speaker-Independent Speech-Driven Visual Speech Synthesis u..:

, In: 2019 International Conference on Multimodal Interaction,

Hussen Abdelaziz, Ahmed ; Theobald, Barry-John ; Binder, Justin... - p. 220-225 , 2019

Link: https://dl.acm.org/doi/1..

4

Learning Dynamic Stream Weights For Coupled-HMM-based Audio..:

Hussen Abdelaziz, Ahmed ; Zeiler, Steffen ; Kolossa, Dorothea
IEEE/ACM Transactions on Audio, Speech, and Language Processing. , 2015

Link: https://doi.org/10.1109/..

5

Modality Drop-Out for Multimodal Device Directed Speech Det..:

, In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Krishna, Gautam ; Dharur, Sameer ; Rudovic, Oggi... - p. 8240-8244 , 2024

Link: https://doi.org/10.1109/..

6

Comparing Fusion Models for DNN-Based Audiovisual Continuou..:

Abdelaziz, Ahmed Hussen
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP). 26 (2018) 3 - p. 475-484 , 2018

Link: https://dl.acm.org/doi/1..

7

Comparing Fusion Models for DNN-Based Audiovisual Continuou..:

Abdelaziz, Ahmed Hussen
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 26 (2018) 3 - p. 475-484 , 2018

Link: https://doi.org/10.1109/..

8

General hybrid framework for uncertainty-decoding-based aut..:

Abdelaziz, Ahmed Hussen ; Kolossa, Dorothea
Speech Communication. 79 (2016) - p. 1-13 , 2016

Link: https://doi.org/10.1016/..

9

Learning dynamic stream weights for coupled-HMM-based audio..:

Abdelaziz, Ahmed Hussen ; Zeiler, Steffen ; Kolossa, Dorothea
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP). 23 (2015) 5 - p. 863-876 , 2015

Link: https://dl.acm.org/doi/1..

10

NTCD-TIMIT:

Hussen Abdelaziz, Ahmed
doi:10.5281/zenodo.787891. , 2017

Link: https://zenodo.org/recor..

11

NTCD-TIMIT:

Hussen Abdelaziz, Ahmed
doi:10.5281/zenodo.787891. , 2017

Link: https://zenodo.org/recor..

12

Human-robot collaborative tutoring using multiparty multimo..:

, In: Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction,

Al Moubayed, Samer ; Beskow, Jonas ; Bollepalli, Bajibabu... - p. 112-113 , 2014

Link: https://dl.acm.org/doi/1..

13

Noise-robust HMM-based pattern recognition using multimodal..:

Hussen Abdelaziz, Ahmed Serag Eldin (M. Sc.)
https://hss-opus.ub.ruhr-uni-bochum.de/opus4/frontdoor/index/index/docId/4543. , 2016

Link: https://hss-opus.ub.ruhr..

14

ESPnet-SPK: full pipeline speaker embedding toolkit with re..:

Jung, Jee-weon ; Zhang, Wangyou ; Shi, Jiatong...
http://arxiv.org/abs/2401.17230. , 2024

Link: http://arxiv.org/abs/240..

15

Can you Remove the Downstream Model for Speaker Recognition..:

Aldeneh, Zakaria ; Higuchi, Takuya ; Jung, Jee-weon...
http://arxiv.org/abs/2402.00340. , 2024

Link: http://arxiv.org/abs/240..