Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Kusha Sridhar"'
Autor:
Kusha Sridhar, Carlos Busso
Publikováno v:
IEEE Transactions on Affective Computing. 13:1959-1972
The prediction of valence from speech is an important, but challenging problem. The externalization of valence in speech has speaker-dependent cues, which contribute to performances that are often significantly lower than the prediction of other emot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b2a41bd1be0e24647a9f1774f35126e
https://doi.org/10.1109/taffc.2022.3187336
https://doi.org/10.1109/taffc.2022.3187336
Publikováno v:
IEEE Signal Processing Magazine. 38:22-38
Speech emotion recognition (SER) is an important research area, with direct impacts in applications of our daily lives, spanning education, health care, security and defense, entertainment, and human–computer interaction. The advances in many other
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0aba16622070ede66b2a0148c2fbc79
https://doi.org/10.1109/msp.2021.3105939
https://doi.org/10.1109/msp.2021.3105939
Accurately recognizing health-related conditions from wearable data is crucial for improved healthcare outcomes. To improve the recognition accuracy, various approaches have focused on how to effectively fuse information from multiple sensors. Fusing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::652fee1579878ada8c163ac36dc485d5
http://arxiv.org/abs/2202.08267
http://arxiv.org/abs/2202.08267
Publikováno v:
ACII
This paper presents a novel speech emotion recognition (SER) method to capture the uncertainty in predicting emotional attributes using the true distribution of scores provided by annotators as ground truth (i.e., soft-labels). Reliable, generalizabl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fb41d7d19878ce471be4806829d45212
https://doi.org/10.1109/acii52823.2021.9597461
https://doi.org/10.1109/acii52823.2021.9597461
Publikováno v:
ICASSP
Semi-supervised learning (SSL) is an appealing approach to resolve generalization problem for speech emotion recognition (SER) systems. By utilizing large amounts of unlabeled data, SSL is able to gain extra information about the prior distribution o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::58504c968f9d9f6d736d04b6683dc751
https://doi.org/10.1109/icassp39728.2021.9414035
https://doi.org/10.1109/icassp39728.2021.9414035
Autor:
Carlos Busso, Kusha Sridhar
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92722f5ad541fb3214f59de4427ea771
https://doi.org/10.21437/interspeech.2020-2694
https://doi.org/10.21437/interspeech.2020-2694
Autor:
Kusha Sridhar, Carlos Busso
Publikováno v:
ICASSP
A challenging task in affective computing is to build reliable speech emotion recognition (SER) systems that can accurately predict emotional attributes from spontaneous speech. To increase the trust in these SER systems, it is important to predict n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::917c713d746406db5a5d78c0f39392b1
https://doi.org/10.1109/icassp40776.2020.9054237
https://doi.org/10.1109/icassp40776.2020.9054237
Autor:
Sriram Srinivasan, Hannes Gamper, Kusha Sridhar, Sebastian Braun, Tanel Parnamaa, Robert Aichner, Ross Cutler, Ando Saabas, Markus Loide
Publikováno v:
ICASSP
The ICASSP 2021 Acoustic Echo Cancellation Challenge is intended to stimulate research in the area of acoustic echo cancellation (AEC), which is an important part of speech enhancement and still a top issue in audio communication and conferencing sys
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35b79f2ddd44ed649e673810f3af6e39
Autor:
Carlos Busso, Kusha Sridhar
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13b3e57127cfd99bffb0c39aadb3a487
https://doi.org/10.21437/interspeech.2019-1842
https://doi.org/10.21437/interspeech.2019-1842
Publikováno v:
INTERSPEECH
Regularization plays a key role in improving the prediction of emotions using attributes such as arousal, valence and dominance. Regularization is particularly important with deep neural networks (DNNs), which have millions of parameters. While previ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::95b3f690011aae7192739ebf7dcc410f
https://doi.org/10.21437/interspeech.2018-2508
https://doi.org/10.21437/interspeech.2018-2508