1 code implementation • 12 Jul 2023 • Titouan Parcollet, Rogier Van Dalen, Shucong Zhang, Sourav Bhattacharya
Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference as well as training and increasing memory consumption.
no code implementations • 8 Nov 2022 • Shucong Zhang, Malcolm Chadwick, Alberto Gil C. P. Ramos, Sourav Bhattacharya
Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild.
no code implementations • 26 Oct 2021 • Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Timothy Hospedales, Georgios Tzimiropoulos, Nicholas D Lane, Maja Pantic
We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network.
no code implementations • ICLR 2022 • Alberto Gil Couto Pimentel Ramos, Abhinav Mehrotra, Nicholas Donald Lane, Sourav Bhattacharya
Conditional neural networks play an important role in a number of sequence-to-sequence modeling tasks, including personalized sound enhancement (PSE), speaker dependent automatic speech recognition (ASR), and generative modeling such as text-to-speech synthesis.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 4 Mar 2021 • Sourav Bhattacharya, Alexander Blokh
We show that the connectedness of the set of parameters for which the over-rotation interval of a bimodal interval map is constant.
Dynamical Systems
no code implementations • 23 Feb 2021 • Md Sabir Ali, Sourav Bhattacharya, Shankhadeep Chakrabortty, Shagun Kaushal
Using the squeezed state expansion, we then demonstrate the Bell violations for the vacuum and some maximally entangled initial states.
High Energy Physics - Theory General Relativity and Quantum Cosmology
no code implementations • 20 Jan 2021 • Sourav Bhattacharya, Alexander Blokh, Dierk Schleicher
In the end we verify the \emph{Fatou conjecture} for the unicritical laminations and extend the \emph{Lavaurs algorithm} onto $\mathrm{UML}_d$.
Dynamical Systems Primary: 54F20, Secondary: 30C35
1 code implementation • ICLR 2021 • Abhinav Mehrotra, Alberto Gil C. P. Ramos, Sourav Bhattacharya, Łukasz Dudziak, Ravichander Vipperla, Thomas Chau, Mohamed S Abdelfattah, Samin Ishtiaq, Nicholas Donald Lane
These datasets, however, focus predominantly on computer vision and NLP tasks and thus suffer from the problem of limited coverage of application domains.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 11 Aug 2020 • Ravichander Vipperla, Sangjun Park, Kihyun Choo, Samin Ishtiaq, Kyoungbo Min, Sourav Bhattacharya, Abhinav Mehrotra, Alberto Gil C. P. Ramos, Nicholas D. Lane
LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low.
no code implementations • 6 Aug 2020 • Abhinav Mehrotra, Łukasz Dudziak, Jinsu Yeo, Young-Yoon Lee, Ravichander Vipperla, Mohamed S. Abdelfattah, Sourav Bhattacharya, Samin Ishtiaq, Alberto Gil C. P. Ramos, SangJeong Lee, Daehyun Kim, Nicholas D. Lane
Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 25 Sep 2019 • Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Georgios Tzimiropoulos, Nicholas D. Lane, Maja Pantic
As deep neural networks become widely adopted for solving most problems in computer vision and audio-understanding, there are rising concerns about their potential vulnerability.
no code implementations • 21 Aug 2019 • Royson Lee, Stylianos I. Venieris, Łukasz Dudziak, Sourav Bhattacharya, Nicholas D. Lane
In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR).
no code implementations • ICLR 2019 • Royson Lee, Nic Lane, Marko Stankovic, Sourav Bhattacharya
A successful application of convolutional architectures is to increase the resolution of single low-resolution images -- a image restoration task called super-resolution (SR).
no code implementations • 23 Sep 2017 • Petar Veličković, Laurynas Karazija, Nicholas D. Lane, Sourav Bhattacharya, Edgar Liberis, Pietro Liò, Angela Chieh, Otmane Bellahsen, Matthieu Vegreville
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements.
no code implementations • 25 Dec 2013 • Sourav Bhattacharya, Petteri Nurmi, Nils Hammerla, Thomas Plötz
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches.