Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Yanxiong Li"'
Publikováno v:
IEEE Access, Vol 6, Pp 58043-58055 (2018)
Surveillance systems based on image analysis can automatically detect road accidents to ensure a quick intervention by rescue teams. However, in some situations, the visual information is insufficiently reliable, whereas the use of a sound detector c
Externí odkaz:
https://doaj.org/article/eebc7f2e129f496bb2746ea6ce4b5f4b
Recent efforts have been made on acoustic scene classification in the audio signal processing community. In contrast, few studies have been conducted on acoustic scene clustering, which is a newly emerging problem. Acoustic scene clustering aims at m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5d4c1d23b22a4ddac81492b98477e5dc
http://arxiv.org/abs/2306.05621
http://arxiv.org/abs/2306.05621
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c00e86063ded3ffb7a2eefc0f5726da1
https://doi.org/10.1109/icassp49357.2023.10096778
https://doi.org/10.1109/icassp49357.2023.10096778
Existing methods for few-shot speaker identification (FSSI) obtain high accuracy, but their computational complexities and model sizes need to be reduced for lightweight applications. In this work, we propose a FSSI method using a lightweight prototy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8789cf3335f3e398229331690697bde4
http://arxiv.org/abs/2305.19541
http://arxiv.org/abs/2305.19541
Publikováno v:
Applied Sciences, Vol 11, Iss 10, p 4699 (2021)
Label Smoothing Regularization (LSR) is a widely used tool to generalize classification models by replacing the one-hot ground truth with smoothed labels. Recent research on LSR has increasingly focused on the correlation between the LSR and Knowledg
Externí odkaz:
https://doaj.org/article/27753f7ef7534103b22decf9c1d81461
Publikováno v:
Sensors, Vol 21, Iss 8, p 2792 (2021)
Knowledge Distillation (KD), which transfers the knowledge from a teacher to a student network by penalizing their Kullback–Leibler (KL) divergence, is a widely used tool for Deep Neural Network (DNN) compression in intelligent sensor systems. Trad
Externí odkaz:
https://doaj.org/article/97a6502cc6c241f89be47666b80f7f62
Publikováno v:
Multimedia Systems. 28:1481-1494
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dc780a8a2142b766dea4d0fdb21e33c1
https://doi.org/10.1007/s00530-022-00915-9
https://doi.org/10.1007/s00530-022-00915-9
Publikováno v:
Multimedia Tools and Applications. 81:6943-6956
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c5eceac293e170ce1cdf5bbbc43042b
https://doi.org/10.1007/s11042-022-12018-8
https://doi.org/10.1007/s11042-022-12018-8
Publikováno v:
IEEE Transactions on Multimedia. :1-12
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e07cd1e966b5a16600179c91dbeb6cca
https://doi.org/10.1109/tmm.2022.3184533
https://doi.org/10.1109/tmm.2022.3184533
Most existing methods for audio classification assume that the vocabulary of audio classes to be classified is fixed. When novel (unseen) audio classes appear, audio classification systems need to be retrained with abundant labeled samples of all aud
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d026ed9596cd95db7c1e6d808518a95c