Related papers: ASAP-FE: Energy-Efficient Feature Extraction Enabl…
Spatial information is a critical clue for multi-channel multi-speaker target speech recognition. Most state-of-the-art multi-channel Automatic Speech Recognition (ASR) systems extract spatial features only during the speech separation…
We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…
The Keyword Spotting (KWS) task involves continuous audio stream monitoring to detect predefined words, requiring low energy devices for continuous processing. Neuromorphic devices effectively address this energy challenge. However, the…
The 6G mobile networks feature two new usage scenarios -- distributed sensing and edge artificial intelligence (AI). Their natural integration, termed integrated sensing and edge AI (ISEA), promises to create a platform that enables…
Customized keyword spotting (KWS) has great potential to be deployed on edge devices to achieve hands-free user experience. However, in real applications, false alarm (FA) would be a serious problem for spotting dozens or even hundreds of…
This work presents TREA, a low-precision time-multiplexed and resource-efficient edge-AI accelerator for object detection and classification, targeting stringent area-power-latency constraints of edge vision platforms. The proposed…
The device-edge co-inference paradigm effectively bridges the gap between the high resource demands of Graph Neural Networks (GNNs) and limited device resources, making it a promising solution for advancing edge GNN applications. Existing…
Energy efficiency is a key requirement in the design of wireless sensor networks. While most theoretical studies only account for the energy requirements of communication, the sensing process, which includes measurements and compression,…
Keyword spotting (KWS) is an important technique for speech applications, which enables users to activate devices by speaking a keyword phrase. Although a phoneme classifier can be used for KWS, exploiting a large amount of transcribed data…
The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on…
Over-the-air federated edge learning (Air-FEEL) is a communication-efficient solution for privacy-preserving distributed learning over wireless networks. Air-FEEL allows "one-shot" over-the-air aggregation of gradient/model-updates by…
Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…
This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically…
Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural…
Stacked AutoEncoders (SAE) have been widely adopted in edge anomaly detection scenarios. However, the resource-intensive nature of SAE can pose significant challenges for edge devices, which are typically resource-constrained and must adapt…
Circuit discovery is a key step in many mechanistic interpretability pipelines. Current methods, such as Path Patching, are computationally expensive and have limited in-depth circuit analysis for smaller models. In this study, we propose…
Standard frame-based cameras that sample light intensity frames are heavily impacted by motion blur for high-speed motion and fail to perceive scene accurately when the dynamic range is high. Event-based cameras, on the other hand, overcome…
Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies like binarization are studied to…
Developing a single-microphone speech denoising or dereverberation front-end for robust automatic speaker verification (ASV) in noisy far-field speaking scenarios is challenging. To address this problem, we present a novel front-end design…
Data accesses between on- and off-chip memories account for a large fraction of overall energy consumption during inference with deep learning networks. We present APack, a simple and effective, lossless, off-chip memory compression…