Zobrazeno 1 - 10
of 12
pro vyhledávání: '"A N Escalante-B"'
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30:2716-2728
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e3ae5c48af2325dc47b07fd8d27c8ae
https://doi.org/10.1109/taslp.2022.3198548
https://doi.org/10.1109/taslp.2022.3198548
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9b3018f024d161ffdfd85a2298507a4
https://doi.org/10.21437/interspeech.2021-633
https://doi.org/10.21437/interspeech.2021-633
Autor:
Alberto N. Escalante-B., Sascha Disch, Metehan Yurt, Pavan Kantharaju, Andreas Niedermeier, Veniamin I. Morgenshtern
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9fa0a2d025b4459294d76403957eb821
https://doi.org/10.21437/interspeech.2021-645
https://doi.org/10.21437/interspeech.2021-645
Publikováno v:
Machine Learning. 109:999-1037
Slow feature analysis (SFA) is an unsupervised-learning algorithm that extracts slowly varying features from a multi-dimensional time series. A supervised extension to SFA for classification and regression is graph-based SFA (GSFA). GSFA is based on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd22adefc88bdf8771ea6b51465cfdcd
https://doi.org/10.1007/s10994-019-05860-9
https://doi.org/10.1007/s10994-019-05860-9
Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks (CM) are usu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a069b6d07ad4468b76a1cd62b69198f
Publikováno v:
INTERSPEECH
Deep-learning based noise reduction algorithms have proven their success especially for non-stationary noises, which makes it desirable to also use them for embedded devices like hearing aids (HAs). This, however, is currently not possible with state
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcd1f4e995ab4bdfe890dca706649f79
https://doi.org/10.21437/interspeech.2020-1131
https://doi.org/10.21437/interspeech.2020-1131
Publikováno v:
ICASSP
Noise reduction is an important part of modern hearing aids and is included in most commercially available devices. Deep learning-based state-of-the-art algorithms, however, either do not consider real-time and frequency resolution constrains or resu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08f88b697759cd7c52680e87d583d3ea
http://arxiv.org/abs/2001.10218
http://arxiv.org/abs/2001.10218
Publikováno v:
ICPRAM
In this paper, we propose a new experimental protocol and use it to benchmark the data efficiency --- performance as a function of training set size --- of two deep learning algorithms, convolutional neural networks (CNNs) and hierarchical informatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47648f793357288c9ef3680c87d13e1c
Publikováno v:
KI - Künstliche Intelligenz. 26:341-348
Slow Feature Analysis (SFA) is an unsupervised learning algorithm based on the slowness principle and has originally been developed to learn invariances in a model of the primate visual system. Although developed for computational neuroscience, SFA h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f366c3a5b2b0fce6b574e1838abb11e
https://doi.org/10.1007/s13218-012-0190-7
https://doi.org/10.1007/s13218-012-0190-7