no code implementations • 22 Sep 2023 • Arnab Das, Suhita Ghosh, Sebastian Stober
Further, the representations from different branches act complementary to each other at the second stage of training, where they are fine-tuned through an unsupervised loss.
1 code implementation • 14 Sep 2023 • Arnab Das, Suhita Ghosh, Tim Polzehl, Sebastian Stober
In this paper, we show that StarGANv2-VC fails to disentangle the speaker and emotion representations, pertinent to preserve emotion.
1 code implementation • 14 Sep 2023 • Suhita Ghosh, Arnab Das, Yamini Sinha, Ingo Siegert, Tim Polzehl, Sebastian Stober
Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content.
1 code implementation • 16 Oct 2021 • Soumick Chatterjee, Arnab Das, Chirag Mandal, Budhaditya Mukhopadhyay, Manish Vipinraj, Aniruddh Shukla, Rajatha Nagaraja Rao, Chompunuch Sarasaen, Oliver Speck, Andreas Nürnberger
Moreover, this research presents a unified framework, TorchEsegeta, for applying various interpretability and explainability techniques for deep learning models and generate visual interpretations and explanations for clinicians to corroborate their clinical findings.
no code implementations • 9 Sep 2019 • Asmi Haldar, Diptiman Sen, Roderich Moessner, Arnab Das
We consider a clean quantum system subject to strong periodic driving.
Other Condensed Matter Statistical Mechanics Quantum Physics
no code implementations • 15 Jan 2008 • Arnab Das, Bikas K. Chakrabarti
We review here the recent success in quantum annealing, i. e., optimization of the cost or energy functions of complex systems utilizing quantum fluctuations.
Quantum Physics Statistical Mechanics Computational Physics