Zobrazeno 1 - 10
of 3 470
pro vyhledávání: '"Sekhar C"'
Training Memory-based transformers can require a large amount of memory and can be quite inefficient. We propose a novel two-phase training mechanism and a novel regularization technique to improve the training efficiency of memory-based transformers
Externí odkaz:
http://arxiv.org/abs/2311.08123
Autor:
Ojha, Rupam, Sekhar, C Chandra
Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different accent and var
Externí odkaz:
http://arxiv.org/abs/2108.02850
Autor:
Dawalatabad, Nauman, Sebastian, Jilt, Kuriakose, Jom, Sekhar, C. Chandra, Narayanan, Shrikanth, Murthy, Hema A.
Instrument separation in an ensemble is a challenging task. In this work, we address the problem of separating the percussive voices in the taniavartanam segments of Carnatic music. In taniavartanam, a number of percussive instruments play together o
Externí odkaz:
http://arxiv.org/abs/2103.03215
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, 2021, pp 14-27
Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly distributing spea
Externí odkaz:
http://arxiv.org/abs/2010.06304
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Sekhar, C. S. C.1 (AUTHOR), Thapa, Namrata1 (AUTHOR) namrata.thapa@iegindia.org
Publikováno v:
Development Policy Review. Sep2023, Vol. 41 Issue 5, p1-24. 24p. 2 Diagrams, 11 Charts, 2 Graphs.
The two-pass information bottleneck (TPIB) based speaker diarization system operates independently on different conversational recordings. TPIB system does not consider previously learned speaker discriminative information while diarizing new convers
Externí odkaz:
http://arxiv.org/abs/1902.08051
Autor:
Yan, Jingya, Kothur, Kavitha, Mohammad, Shekeeb, Chung, Jason, Patel, Shrujna, Jones, Hannah F., Keating, Brooke A., Han, Velda X., Webster, Richard, Ardern-Holmes, Simone, Antony, Jayne, Menezes, Manoj P., Tantsis, Esther, Gill, Deepak, Gupta, Sachin, Kandula, Tejaswi, Sampaio, Hugo, Farrar, Michelle A., Troedson, Christopher, Andrews, P Ian, Pillai, Sekhar C., Heng, Benjamin, Guillemin, Gilles J., Guller, Anna, Bandodkar, Sushil, Dale, Russell C.
Publikováno v:
In eBioMedicine May 2023 91
Autor:
Jingya Yan, Kavitha Kothur, Shekeeb Mohammad, Jason Chung, Shrujna Patel, Hannah F. Jones, Brooke A. Keating, Velda X. Han, Richard Webster, Simone Ardern-Holmes, Jayne Antony, Manoj P. Menezes, Esther Tantsis, Deepak Gill, Sachin Gupta, Tejaswi Kandula, Hugo Sampaio, Michelle A. Farrar, Christopher Troedson, P Ian Andrews, Sekhar C. Pillai, Benjamin Heng, Gilles J. Guillemin, Anna Guller, Sushil Bandodkar, Russell C. Dale
Publikováno v:
EBioMedicine, Vol 91, Iss , Pp 104589- (2023)
Summary: Background: Defining the presence of acute and chronic brain inflammation remains a challenge to clinicians due to the heterogeneity of clinical presentations and aetiologies. However, defining the presence of neuroinflammation, and monitori
Externí odkaz:
https://doaj.org/article/f3f98b36f0cb49b9aa7418bacef1fbf5
Autor:
Sekhar C. Ray
Publikováno v:
AIP Advances, Vol 13, Iss 3, Pp 035028-035028-5 (2023)
The temperature-dependent resistivity, room temperature electron field emission, and magnetic performance within the temperature range of 2–300 K of previously chemically synthesized pure carbon nanoparticles (CNPs) from candle soot having particle
Externí odkaz:
https://doaj.org/article/b31cc2ebad214f319e8ce1296607faed