Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Gil Keren"'
Publikováno v:
IEEE Access, Vol 6, Pp 54033-54041 (2018)
Ongoing developments in neural network models are continually advancing the state-of-the-art in terms of system accuracy. However, the predicted labels should not be regarded as the only core output; also important is a well-calibrated estimate of th
Externí odkaz:
https://doaj.org/article/6eb1b58b05d44d76a623afb64152fb7a
Autor:
Björn Schuller, Alice Baird, Maximilian Schmitt, Alexander Gebhard, Nicholas Cummins, Shahin Amiriparian, Gil Keren
Publikováno v:
Trends in Hearing
Computer audition (i.e., intelligent audio) has made great strides in recent years; however, it is still far from achieving holistic hearing abilities, which more appropriately mimic human-like understanding. Within an audio scene, a human listener i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf93940ff0ba389e7937b88c39e5bf74
https://pubmed.ncbi.nlm.nih.gov/34751066
https://pubmed.ncbi.nlm.nih.gov/34751066
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dc2183d424b4bbd4b6b5f776d268f561
https://doi.org/10.21437/interspeech.2021-1941
https://doi.org/10.21437/interspeech.2021-1941
Publikováno v:
ICASSP
Packet loss may affect a wide range of applications that use voice over IP (VoIP), e.g. video conferencing. In this paper, we investigate a time-domain convolutional recurrent network (CRN) for online packet loss concealment. The CRN comprises a conv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::73c7b38a38c5cc735b1c857de9f250cd
https://doi.org/10.1109/icassp39728.2021.9413595
https://doi.org/10.1109/icassp39728.2021.9413595
Autor:
Yatharth Saraf, Michael L. Seltzer, Suyoun Kim, Christian Fuegen, Duc Le, Yangyang Shi, Ozlem Kalinli, Julian Chan, Gil Keren, Yuan Shangguan, Mahaveer Jain, Jay Mahadeokar
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to open-domain scenar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e25c8e6ece4b166bb1d6fa115444004
Autor:
Weiyi Zheng, Alex Xiao, Gil Keren, Duc Le, Frank Zhang, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Abdelrahman Mohamed
With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to efficiently
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75de3266af06b98ab25a97f6b1731a06
Publikováno v:
SLT
End-to-end models in general, and Recurrent Neural Network Transducer (RNN-T) in particular, have gained significant traction in the automatic speech recognition community in the last few years due to their simplicity, compactness, and excellent perf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::86750227894056aaf734326e2e56c048
http://arxiv.org/abs/2011.07754
http://arxiv.org/abs/2011.07754
Autor:
Thong Le, Hang Su, Yuan Shangguan, Michael L. Seltzer, Ching-Feng Yeh, Gil Keren, Christian Fuegen, Duc Le, Jay Mahadeokar
Publikováno v:
SLT
There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal alignment o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b05f12207930f1cd1cec3034b966ba40
http://arxiv.org/abs/2011.03072
http://arxiv.org/abs/2011.03072
Publikováno v:
INTERSPEECH
End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a traditional hybrid ASR system - acoustic model, language model, pronunciation model - i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d966be3d1aa2f67fc055b38bab572599
https://doi.org/10.21437/interspeech.2020-2986
https://doi.org/10.21437/interspeech.2020-2986
Publikováno v:
The Journal of Symbolic Logic. 82:1482-1495
We prove that all known examples of weakly o-minimal nonvaluational structures have no definable Skolem functions. We show, however, that such structures eliminate imaginaries up to definable families of cuts. Along the way we give some new examples
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::621d6cb1f5966ba04614f8aa683c1259
https://doi.org/10.1017/jsl.2017.28
https://doi.org/10.1017/jsl.2017.28