Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Chaitanya Talnikar"'
Publikováno v:
ICASSP
Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec~2.0 requires a two-stage pipeline. In this paper we demonstrate a sing
Autor:
Chaitanya Talnikar, Qiqi Wang
Publikováno v:
Parallel Computing. 81:68-84
The adjoint method is a useful tool for finding gradients of design objectives with respect to system parameters for fluid dynamics simulations. But the utility of this method is hampered by the difficulty in writing an efficient implementation for t
Autor:
Daniel Haziza, Changhan Wang, Morgane Riviere, Juan Pino, Anne Wu, Ann B. Lee, Mary Williamson, Chaitanya Talnikar, Emmanuel Dupoux
Publikováno v:
2021, ⟨10.18653/v1/2021.acl-long.80⟩
ACL/IJCNLP (1)
ACL 2021-59th Annual Meeting of the Association for Computational Linguistics
ACL 2021-59th Annual Meeting of the Association for Computational Linguistics, Aug 2021, Bangkok, Thailand
ACL/IJCNLP (1)
ACL 2021-59th Annual Meeting of the Association for Computational Linguistics
ACL 2021-59th Annual Meeting of the Association for Computational Linguistics, Aug 2021, Bangkok, Thailand
We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning as well as semi-supervised learning. VoxPopuli also
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::31dab65f924fddb10ab121a9ba5bccc4
Autor:
Chaitanya Talnikar, Angxiu Ni
We develop the NILSAS algorithm, which performs adjoint sensitivity analysis of chaotic systems via computing the adjoint shadowing direction. NILSAS constrains its minimization to the adjoint unstable subspace, and can be implemented with little mod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::facfb4f9750e64746dc5de6c02d21609
Publikováno v:
arXiv
In chaotic systems, such as turbulent flows, the solutions to tangent and adjoint equations exhibit an unbounded growth in their norms. This behavior renders the instantaneous tangent and adjoint solutions unusable for sensitivity analysis. The Lea-A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a984df5db07bb9ba007ad30f9f5a7aa1
Publikováno v:
Other repository
We present the Finite Difference Non-Intrusive Least Squares Shadowing (FD-NILSS) algorithm for computing sensitivities of long-time averaged quantities in chaotic dynamical systems. FD-NILSS does not require tangent solvers, and can be implemented w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::25625b726d8e4c769178bf32a27bc2ee
http://arxiv.org/abs/1711.06633
http://arxiv.org/abs/1711.06633
Publikováno v:
23rd AIAA Computational Fluid Dynamics Conference.
Publikováno v:
Journal of Turbomachinery. 139
High fidelity simulations, e.g., large eddy simulation are often needed for accurately predicting pressure losses due to wake mixing in turbomachinery applications. An unsteady adjoint of such high fidelity simulations is useful for design optimizati
Publikováno v:
Applied Mechanics and Materials. 232:388-391
This paper proposes a technology to automate the book deposition process in a generic Library layout. It includes usage of autonomous vehicle in the library that is guided by an assembly of lasers. To prove the practicability of this proposal a physi
Autor:
Gregory M. Laskowski, Umesh Paliath, Sriram Shankaran, Qiqi Wang, James Kopriva, Rathakrishnan Bhaskaran, Feilin Jia, Zhi J. Wang, Vittorio Michelassi, Chaitanya Talnikar
Publikováno v:
46th AIAA Fluid Dynamics Conference.