Zobrazeno 1 - 10
of 3 189
pro vyhledávání: '"SHANKAR, RAVI"'
Autor:
Viswanathan, Sruthi, Ibrahim, Seray, Shankar, Ravi, Binns, Reuben, Van Kleek, Max, Slovak, Petr
Parenting brings emotional and physical challenges, from balancing work, childcare, and finances to coping with exhaustion and limited personal time. Yet, one in three parents never seek support. AI systems potentially offer stigma-free, accessible,
Externí odkaz:
http://arxiv.org/abs/2411.01228
Autor:
Shankar, Ravi, Venkataraman, Archana
In this paper, we propose the first method to modify the prosodic features of a given speech signal using actor-critic reinforcement learning strategy. Our approach uses a Bayesian framework to identify contiguous segments of importance that links se
Externí odkaz:
http://arxiv.org/abs/2408.01892
Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech recognition and
Externí odkaz:
http://arxiv.org/abs/2403.01369
Autor:
Shankar, Ravi
New, doubling proofs are given for the interior Hessian estimates of the special Lagrangian equation. These estimates were originally shown by Chen-Warren-Yuan in CPAM 2009 and Wang-Yuan in AJM 2014. This yields a higher codimension analogue of Korev
Externí odkaz:
http://arxiv.org/abs/2401.01034
Autor:
Shankar, Ravi, Yuan, Yu
We derive a priori interior Hessian estimates and interior regularity for the $\sigma_2$ equation in dimension four. Our method provides respectively a new proof for the corresponding three dimensional results and a Hessian estimate for smooth soluti
Externí odkaz:
http://arxiv.org/abs/2305.12587
Publikováno v:
Benchmarking: An International Journal, 2023, Vol. 31, Issue 5, pp. 1453-1491.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/BIJ-04-2022-0273
Publikováno v:
Main Group Metal Chemistry, Vol 33, Iss 4-5, Pp 201-204 (2010)
Externí odkaz:
https://doaj.org/article/33c8111656b94424946e18dcb8f58ccd
This paper introduces a new framework for non-parallel emotion conversion in speech. Our framework is based on two key contributions. First, we propose a stochastic version of the popular CycleGAN model. Our modified loss function introduces a Kullba
Externí odkaz:
http://arxiv.org/abs/2211.05071
Automated emotion recognition in speech is a long-standing problem. While early work on emotion recognition relied on hand-crafted features and simple classifiers, the field has now embraced end-to-end feature learning and classification using deep n
Externí odkaz:
http://arxiv.org/abs/2211.05047