Zobrazeno 1 - 10
of 161
pro vyhledávání: '"P. Narisetty"'
Autor:
Vinod Kumar, Pankaj Kumar, Sunil K. Maity, Deepti Agrawal, Vivek Narisetty, Samuel Jacob, Gopalakrishnan Kumar, Shashi Kant Bhatia, Dinesh Kumar, Vivekanand Vivekanand
Publikováno v:
Biotechnology for Biofuels and Bioproducts, Vol 17, Iss 1, Pp 1-39 (2024)
Abstract Succinic acid (SA) is one of the top platform chemicals with huge applications in diverse sectors. The presence of two carboxylic acid groups on the terminal carbon atoms makes SA a highly functional molecule that can be derivatized into a w
Externí odkaz:
https://doaj.org/article/8130f3e665034e64aa54c8a9866cce17
End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio--text data. Recent studies estimate a linguistic bias of the model as the internal language mode
Externí odkaz:
http://arxiv.org/abs/2206.07430
Autor:
Narisetty, Chaitanya, Tsunoo, Emiru, Chang, Xuankai, Kashiwagi, Yosuke, Hentschel, Michael, Watanabe, Shinji
Speech samples recorded in both indoor and outdoor environments are often contaminated with secondary audio sources. Most end-to-end monaural speech recognition systems either remove these background sounds using speech enhancement or train noise-rob
Externí odkaz:
http://arxiv.org/abs/2202.01405
A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding algorithm with a
Externí odkaz:
http://arxiv.org/abs/2201.10190
In this paper, we consider the multi-armed bandit problem with high-dimensional features. First, we prove a minimax lower bound, $\mathcal{O}\big((\log d)^{\frac{\alpha+1}{2}}T^{\frac{1-\alpha}{2}}+\log T\big)$, for the cumulative regret, in terms of
Externí odkaz:
http://arxiv.org/abs/2109.11612
We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on generative commonsense reason
Externí odkaz:
http://arxiv.org/abs/2108.06643
Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust against noisy and low-resource conditions. In this study, we investigate
Externí odkaz:
http://arxiv.org/abs/2106.03419
Soils have been heralded as a hidden resource that can be leveraged to mitigate and address some of the major global environmental challenges. Specifically, the organic carbon stored in soils, called Soil Organic Carbon (SOC), can, through proper soi
Externí odkaz:
http://arxiv.org/abs/2102.02731
Autor:
Rendra Hakim Hafyan, Jasmithaa Mohanarajan, Manaal Uppal, Vinod Kumar, Vivek Narisetty, Sunil K. Maity, Jhuma Sadhukhan, Siddharth Gadkari
Publikováno v:
Frontiers in Sustainable Food Systems, Vol 8 (2024)
Bread waste (BW) poses a significant environmental and economic challenge in the United Kingdom (UK), where an estimated 20 million slices of bread are wasted daily. BW contains polysaccharides with great potential for its valorization into building
Externí odkaz:
https://doaj.org/article/28fed75bfca5418581e3624cf2a5eb96
Autor:
Boss, Jonathan, Rix, Alexander, Chen, Yin-Hsiu, Narisetty, Naveen N., Wu, Zhenke, Ferguson, Kelly K., McElrath, Thomas F., Meeker, John D., Mukherjee, Bhramar
Publikováno v:
Environmetrics 2021:32(8);e2698
Environmental health studies are increasingly measuring multiple pollutants to characterize the joint health effects attributable to exposure mixtures. However, the underlying dose-response relationship between toxicants and health outcomes of intere
Externí odkaz:
http://arxiv.org/abs/2003.12844