296 citations · 1.5k across the 45 of their papers we have counts for
22 papers · 1 filter
Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
Chongyang Wang, Yuan Gao, Akhil Mathur +3
Protective behavior exhibited by people with chronic pain (CP) during physical activities is the key to understanding their physical and emotional states. Existing automatic protec…
Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
Royson Lee, Stylianos I. Venieris, Nicholas D. Lane
Internet-enabled smartphones and ultra-wide displays are transforming a variety of visual apps spanning from on-demand movies and 360-degree videos to video-conferencing and live s…
Deep Learning in the Era of Edge Computing: Challenges and Opportunities
Mi Zhang, Faen Zhang, Nicholas D. Lane +5
The era of edge computing has arrived. Although the Internet is the backbone of edge computing, its true value lies at the intersection of gathering data from sensors and extractin…
NAS: Constrained Neural Architecture Search for Microcontrollers
Edgar Liberis, Łukasz Dudziak, Nicholas D. Lane
IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persist…
Can Federated Learning Save The Planet?
Xinchi Qiu, Titouan Parcollet, Daniel J. Beutel +3
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers.…
Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
Akhil Mathur, Fahim Kawsar, Nadia Berthouze +1
This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models. Built on top of the LibriSpeech corpus, Libri-Ada…
SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
Stefanos Laskaridis, Stylianos I. Venieris, Mario Almeida +2
Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excess…
Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
Ravichander Vipperla, Sangjun Park, Kihyun Choo +6
LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low. In this work, we present two techniques to…
HAPI: Hardware-Aware Progressive Inference
Stefanos Laskaridis, Stylianos I. Venieris, Hyeji Kim +1
Convolutional neural networks (CNNs) have recently become the state-of-the-art in a diversity of AI tasks. Despite their popularity, CNN inference still comes at a high computation…
Iterative Compression of End-to-End ASR Model using AutoML
Abhinav Mehrotra, Łukasz Dudziak, Jinsu Yeo +9
Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques. Past research hav…
Degree-Quant: Quantization-Aware Training for Graph Neural Networks
Shyam A. Tailor, Javier Fernandez-Marques, Nicholas D. Lane
Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data. Despite their promise, there…
Journey Towards Tiny Perceptual Super-Resolution
Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah +4
Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks.…
Flower: A Friendly Federated Learning Research Framework
Daniel J. Beutel, Taner Topal, Akhil Mathur +8
Federated Learning (FL) has emerged as a promising technique for edge devices to collaboratively learn a shared prediction model, while keeping their training data on the device, t…
BRP-NAS: Prediction-based NAS using GCNs
Łukasz Dudziak, Thomas Chau, Mohamed S. Abdelfattah +3
Neural architecture search (NAS) enables researchers to automatically explore broad design spaces in order to improve efficiency of neural networks. This efficiency is especially i…
IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition
Hyeokhyen Kwon, Catherine Tong, Harish Haresamudram +4
The lack of large-scale, labeled data sets impedes progress in developing robust and generalized predictive models for on-body sensor-based human activity recognition (HAR). Labele…
Quaternion Neural Networks for Multi-channel Distant Speech Recognition
Xinchi Qiu, Titouan Parcollet, Mirco Ravanelli +2
Despite the significant progress in automatic speech recognition (ASR), distant ASR remains challenging due to noise and reverberation. A common approach to mitigate this issue con…
Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech Recognition
Yan Gao, Titouan Parcollet, Nicholas Lane
Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of A…
Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systems
Akhil Mathur, Anton Isopoussu, Fahim Kawsar +2
Mobile and embedded devices are increasingly using microphones and audio-based computational models to infer user context. A major challenge in building systems that combine audio…
Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator
Mohamed S. Abdelfattah, Łukasz Dudziak, Thomas Chau +3
Neural architecture search (NAS) has been very successful at outperforming human-designed convolutional neural networks (CNN) in accuracy, and when hardware information is present,…
The Final Frontier: Deep Learning in Space
Vivek Kothari, Edgar Liberis, Nicholas D. Lane
Machine learning, particularly deep learning, is being increasing utilised in space applications, mirroring the groundbreaking success in many earthbound problems. Deploying a spac…
Are Accelerometers for Activity Recognition a Dead-end?
Catherine Tong, Shyam A. Tailor, Nicholas D. Lane
Accelerometer-based (and by extension other inertial sensors) research for Human Activity Recognition (HAR) is a dead-end. This sensor does not offer enough information for us to p…
EMOPAIN Challenge 2020: Multimodal Pain Evaluation from Facial and Bodily Expressions
Joy O. Egede, Siyang Song, Temitayo A. Olugbade +7
The EmoPain 2020 Challenge is the first international competition aimed at creating a uniform platform for the comparison of machine learning and multimedia processing methods of a…