Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Rohan Kumar Das"'
Publikováno v:
APSIPA Transactions on Signal and Information Processing, Vol 13, Iss 1 (2024)
Externí odkaz:
https://doaj.org/article/81d50f1bd4874020a5369f2459d9adb3
Publikováno v:
IEEE Signal Processing Letters. 29:782-786
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c6fc8810706b3d513c7e94348fe252c
https://doi.org/10.1109/lsp.2022.3143036
https://doi.org/10.1109/lsp.2022.3143036
Autor:
Tanmay Khandelwal, Rohan Kumar Das
Publikováno v:
2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3cc28d8973e0f47e7713c74cdc0994f7
https://doi.org/10.1109/iscslp57327.2022.10038009
https://doi.org/10.1109/iscslp57327.2022.10038009
Autor:
Rohith Mars, Rohan Kumar Das
Publikováno v:
2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6a8dd59faec2f1bf1147f8ea26e2321
https://doi.org/10.1109/iscslp57327.2022.10038050
https://doi.org/10.1109/iscslp57327.2022.10038050
Publikováno v:
2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe4351cd1df67232edbb0d7863022f4b
https://doi.org/10.23919/apsipaasc55919.2022.9980350
https://doi.org/10.23919/apsipaasc55919.2022.9980350
We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance of various
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c67e9debc1d8a57af8de0676c82aba2
http://arxiv.org/abs/2210.15385
http://arxiv.org/abs/2210.15385
Autor:
Longting Xu, Mianxin Tian, Xing Guo, Zhiyong Shan, Jie Jia, Yiyuan Peng, Jichen Yang, Rohan Kumar Das
Publikováno v:
The Speaker and Language Recognition Workshop (Odyssey 2022).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33cc3e427d3889f61e34a89667873809
https://doi.org/10.21437/odyssey.2022-15
https://doi.org/10.21437/odyssey.2022-15
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 29:1065-1078
Most of the existing feature representations for spoofing countermeasures consider information either from the magnitude or phase spectrum. We hypothesize that both magnitude and phase spectra can be beneficial for spoofing detection (SD) when collec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9675964c0da33b98b27561b57b5031c
https://doi.org/10.1109/taslp.2021.3060810
https://doi.org/10.1109/taslp.2021.3060810
Autor:
Teck Kai Chan, Rohan Kumar Das
Publikováno v:
L3DAS22: Machine Learning for 3D Audio Signal Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91291a6713e8c69c5fc0aeb76f8377d3
https://doi.org/10.21437/l3das.2022-3
https://doi.org/10.21437/l3das.2022-3
Publikováno v:
IEEE Transactions on Information Forensics and Security. 15:2160-2170
In text-to-speech or voice conversion based synthetic speech detection, it is a common practice that spectral information over the entire frequency band is used for feature representation. We propose a new method, referred to as subband transform, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d957146b0c23c5620f02d22743596b23
https://doi.org/10.1109/tifs.2019.2956589
https://doi.org/10.1109/tifs.2019.2956589