Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Mohammad Zeineldeen"'
Autor:
Michael Gansen, Jie Lou, Florian Freye, Tobias Gemmeke, Farhad Merchant, Albert Zeyer, Mohammad Zeineldeen, Ralf Schluter, Xin Fan
Publikováno v:
2022 23rd International Symposium on Quality Electronic Design (ISQED).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be54b74394dd632be3217c094503d5e3
https://doi.org/10.1109/isqed54688.2022.9806215
https://doi.org/10.1109/isqed54688.2022.9806215
Autor:
Wei Zhou, Haotian Wu, Jingjing Xu, Mohammad Zeineldeen, Christoph Lüscher, Ralf Schlüter, Hermann Ney
ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain variance towards domain-aware/agnostic ASR, respectively. In this work,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66943f3b2da200ef99349e5dc8d94551
Autor:
Mohammad Zeineldeen, Jingjing Xu, Christoph Luscher, Wilfried Michel, Alexander Gerstenberger, Ralf Schluter, Hermann Ney
The recently proposed conformer architecture has been successfully used for end-to-end automatic speech recognition (ASR) architectures achieving state-of-the-art performance on different datasets. To our best knowledge, the impact of using conformer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7158d86e909375d30e8dc4b1bfe6361
http://arxiv.org/abs/2111.03442
http://arxiv.org/abs/2111.03442
Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM) approach that adapts the adva
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cb8bce336a986f25012f20f933116580
http://arxiv.org/abs/2104.09106
http://arxiv.org/abs/2104.09106
Autor:
Hermann Ney, Aleksandr Glushko, Ralf Schlüter, Wilfried Michel, Albert Zeyer, Mohammad Zeineldeen
Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. The integration with an external LM trained on much more unpaired text usually leads to better performance. A Bayesian inte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08b37caa54398fd315e6c5f3472a0c00
Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to generate syntheti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71e3ffee69ca807e69294c9d91fe3093
Publikováno v:
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP
ICASSP
Training deep neural networks is often challenging in terms of training stability. It often requires careful hyperparameter tuning or a pretraining scheme to converge. Layer normalization (LN) has shown to be a crucial ingredient in training deep enc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b79de047c5d7a00c57f2790f05c40f4