Sourav Bhattacharya

HierarchicalPrune: Position-aware Compression for Large-Scale Diffusion Models

Y.D. Kwon, R. Li, S. Li, D. Li, S. Bhattacharya, S.I. Venieris

Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities

R. Chavhan, A. Mehrotra, M. Chadwick, A.G. Ramos, L. Morreale, M. Noroozi, S. Bhattacharya

EDiT: Efficient Diffusion Transformers with Linear Compressed Attention

P. Becker, A. Mehrotra, R. Chavhan, M. Chadwick, L. Morreale, M. Noroozi, A.G. Ramos, S. Bhattacharya

Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition

T. Parcollet, R. van Dalen, S. Zhang, S. Bhattacharya

Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in LLMs for Speech Recognition

Y. Tseng, T. Parcollet, R. van Dalen, S. Zhang, S. Bhattacharya

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes

R.C. van Dalen, S. Zhang, T. Parcollet, S. Bhattacharya

Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling

Y.D. Kwon, A. Mehrotra, M. Chadwick, A.G. Ramos, S. Bhattacharya

FraQAT: Quantization Aware Training with Fractional Bits

L. Morreale, A.G.C.P. Ramos, M. Chadwick, M. Noroozi, R. Chavhan, A. Mehrotra, S. Bhattacharya

Benchmarking Rotary Position Embeddings for Automatic Speech Recognition

S. Zhang, T. Parcollet, R. van Dalen, S. Bhattacharya

MobileQuant: Mobile-Friendly Quantization for On-Device Language Models

F. Tan, R. Lee, L. Dudziak, S.X. Hu, S. Bhattacharya, T. Hospedales, G. Tzimiropoulos, B. Martinez

SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding

T. Parcollet, R. van Dalen, S. Zhang, S. Bhattacharya

Linear-Complexity Self-Supervised Learning for Speech Processing

S. Zhang, T. Parcollet, R. van Dalen, S. Bhattacharya

On the (In)efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning

T. Parcollet, S. Zhang, R. van Dalen, A.G.C.P. Ramos, S. Bhattacharya

Real-Time Personalised Speech Enhancement Transformers with Dynamic Cross-attended Speaker Representations

S. Zhang, M. Chadwick, A.G.C.P. Ramos, T. Parcollet, R. van Dalen, S. Bhattacharya

Resource Efficient Self-Supervised Learning for Speech Recognition

A. Mehrotra, A.G.C.P. Ramos, N.D. Lane, S. Bhattacharya

Fast Inference Through the Reuse of Attention Maps in Diffusion Models

R. Hunter, L. Dudziak, M.S. Abdelfattah, A. Mehrotra, S. Bhattacharya, H. Wen

Conditioning Sequence-to-Sequence Networks with Learned Activations

A.G.C.P. Ramos, A. Mehrotra, N.D. Lane, S. Bhattacharya

Cross-Attention is All You Need: Real-Time Streaming Transformers for Personalised Speech Enhancement

S. Zhang, M. Chadwick, A.G.C.P. Ramos, S. Bhattacharya

NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech Recognition

A. Mehrotra, A.G.C.P. Ramos, S. Bhattacharya, L. Dudziak, R. Vipperla, T. Chau, M.S. Abdelfattah, S. Ishtiaq, N.D. Lane

Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks

A. Bulat, J. Kossaifi, S. Bhattacharya, Y. Panagakis, T. Hospedales, G. Tzimiropoulos, N.D. Lane, M. Pantic

Countering Acoustic Adversarial Attacks in Microphone-Equipped Smart Home Devices

S. Bhattacharya, D. Manousakas, A. Ramos, S. Venieris, N. Lane, C. Mascolo

Augmenting Conversational Agents with Ambient Acoustic Contexts

C. Park, C. Min, S. Bhattacharya, F. Kawsar

Dynamic Distributed Edge Resource Provisioning via Online Learning across Timescales

W. You, L. Jiao, S. Bhattacharya, Y. Zhang

Iterative Compression of End-to-End ASR Model using AutoML

A. Mehrotra, J. Yeo, Y. Lee, R. Vipperla, M.S. Abdelfattah, S. Bhattacharya et al.

Bunched LPCNet: Vocoder for Low-Cost Neural Text-to-Speech Systems

R. Vipperla, S. Park, K. Choo, S. Ishtiaq, K. Min, S. Bhattacharya et al.

Learning to Listen On-Device: Present and Future Perspectives of On-Device ASR

R. Vipperla, S. Ishtiaq, R. Li, S. Bhattacharya, I. Leontiadis, N.D. Lane

MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors

R. Lee, S.I. Venieris, L. Dudziak, S. Bhattacharya, N.D. Lane

AudiDoS: Real-Time Denial-of-Service Adversarial Attacks on Deep Audio Models

T. Gong, A.G.C.P. Ramos, S. Bhattacharya, A. Mathur, F. Kawsar

Multimodal Deep Learning for Activity and Context Recognition

V. Radu, C. Tong, S. Bhattacharya, N.D. Lane, C. Mascolo, M.K. Marina, F. Kawsar

Deterministic Binary Filters for Convolutional Neural Networks

V.W.-S. Tseng, S. Bhattacharya, J. Fernández-Marqués, M. Alizadeh, C. Tong, N.D. Lane

Using Deep Data Augmentation Training to Address Software and Hardware Heterogeneities in Wearable and Smartphone Sensing

A. Mathur, T. Zhang, S. Bhattacharya, P. Veličković et al.

Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data

P. Veličković, L. Karazija, N.D. Lane, S. Bhattacharya et al.

On-the-Fly Deterministic Binary Filters for Memory Efficient Keyword Spotting on Embedded Devices

J. Fernández-Marqués, V.T.-S. Tseng, S. Bhattacharya, N.D. Lane

Monitoring Daily Activities of Multiple Sclerosis Patients with Connected Health Devices

S. Bhattacharya, A.G.C.P. Ramos, F. Kawsar, N.D. Lane et al.

DeepEye: Resource Efficient Local Execution of Multiple Deep Vision Models using Wearable Commodity Hardware

A. Mathur, N.D. Lane, S. Bhattacharya, A. Boran, C. Forlivesi, F. Kawsar

Squeezing Deep Learning into Mobile and Embedded Devices

N.D. Lane, S. Bhattacharya, A. Mathur, P. Georgiev, C. Forlivesi, F. Kawsar

Low-resource Multi-task Audio Sensing via Shared Deep Neural Network Representations

P. Georgiev, S. Bhattacharya, N.D. Lane, C. Mascolo

Scaling Health Analytics to Millions Without Compromising Privacy using Deep Distributed Behavior Models

P. Veličković, N.D. Lane, S. Bhattacharya et al.

Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables

S. Bhattacharya, N.D. Lane

DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices

N.D. Lane, S. Bhattacharya, P. Georgiev, C. Forlivesi, L. Jiao, L. Qendro, F. Kawsar

From Smart to Deep: Robust Activity Recognition on Smartwatches using Deep Learning

S. Bhattacharya, N.D. Lane

Towards Multimodal Deep Learning for Activity Recognition on Mobile Devices

V. Radu, N.D. Lane, S. Bhattacharya, C. Mascolo, M.K. Marina, F. Kawsar

DXTK: Enabling Resource-Efficient Deep Learning on Mobile and Embedded Devices

N.D. Lane, S. Bhattacharya, A. Mathur, C. Forlivesi, F. Kawsar

Activity Recognition on Smart Devices: Dealing with Diversity in the Wild

H. Blunck, S. Bhattacharya, A. Stisen et al.

Smart Devices are Different: Assessing and Mitigating Mobile Sensing Heterogeneities for Activity Recognition

A. Stisen, H. Blunck, S. Bhattacharya et al.

An Early Resource Characterization of Deep Learning on Wearables, Smartphones and IoT Devices

N.D. Lane, S. Bhattacharya, P. Georgiev, C. Forlivesi, F. Kawsar

LookAhead: Augmenting Crowdsourced Website Reputation Systems with Predictive Modeling

S. Bhattacharya, O. Huhta, N. Asokan

Checksum Gestures: Continuous Gestures as an Out-of-Band Channel for Secure Pairing

I. Ahmed, Y. Ye, S. Bhattacharya, N. Asokan, G. Jacucci, P. Nurmi, S. Tarkoma

Using Unlabeled Data in a Sparse-Coding Framework for Human Activity Recognition

S. Bhattacharya, P. Nurmi, N. Hammerla, T. Plötz

Robust and Energy-Efficient Trajectory Tracking for Mobile Devices

S. Bhattacharya, H. Blunck, M.B. Kjærgaard, P. Nurmi

The Company You Keep: Mobile Malware Infection Rates and Inexpensive Risk Indicators

H.T.T. Truong, E. Lagerspetz, P. Nurmi, A.J. Oliner, S. Tarkoma, N. Asokan, S. Bhattacharya

Gaussian Process-Based Predictive Modeling for Bus Ridership

S. Bhattacharya, S. Phithakkitnukoon, P. Nurmi, A. Klami, M. Veloso, C. Bento

Automatic Correction of Annotation Boundaries in Activity Datasets by Class Separation Maximization

R. Kirkham, A. Khan, S. Bhattacharya, N. Hammerla et al.

Energy-Efficient Trajectory Tracking for Mobile Devices

M.B. Kjærgaard, S. Bhattacharya, H. Blunck, P. Nurmi

Influence of Landmark-Based Navigation Instructions on User Attention in Indoor Smart Spaces

P. Nurmi, A. Salovaara, S. Bhattacharya, T. Pulkkinen, G. Kahl

A Grid-Based Algorithm for On-Device GSM Positioning

P. Nurmi, S. Bhattacharya, J. Kukkonen

Identifying Meaningful Places: The Non-Parametric Way

P. Nurmi, S. Bhattacharya

Markov Property of Continuous Dislocation Band Propagation

A. Chatterjee, A. Sarkar, S. Bhattacharya, P. Mukherjee, N. Gayathri, P. Barat

A Survey on Different Video Watermarking Techniques and Comparative Analysis with H.264/AVC

S. Bhattacharya, T. Chattopadhyay, A. Pal