Related papers: ASAP-FE: Energy-Efficient Feature Extraction Enabl…
Video semantic segmentation (VSS) is a computationally expensive task due to the per-frame prediction for videos of high frame rates. In recent work, compact models or adaptive network strategies have been proposed for efficient VSS.…
For multi-channel speech recognition, speech enhancement techniques such as denoising or dereverberation are conventionally applied as a front-end processor. Deep learning-based front-ends using such techniques require aligned clean and…
The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…
Automatic Speech Recognition (ASR) has shown remarkable progress, yet it still faces challenges in real-world distant scenarios across various array topologies each with multiple recording devices. The focal point of the CHiME-7 Distant ASR…
Recent advancements in head-mounted wearable technology are revolutionizing the field of biopotential measurement, but the integration of these technologies into practical, user-friendly devices remains challenging due to issues with design…
The growing number of Internet-of-Things (IoT) based artificial intelligence (AI) applications deployed at resource-constrained network edge call for ultra-reliable and low-latency data processing pipelines from distributed front-end…
Automatic speech recognition (ASR) provides diverse audio-to-text services for humans to communicate with machines. However, recent research reveals ASR systems are vulnerable to various malicious audio attacks. In particular, by removing…
Realizing edge intelligence consists of sensing, communication, training, and inference stages. Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and…
Audio-visual feature synchronization for real-time speech enhancement in hearing aids represents a progressive approach to improving speech intelligibility and user experience, particularly in strong noisy backgrounds. This approach…
Why do security cameras, sensors, and siri use cloud servers instead of on-board computation? The lack of very-low-power, high-performance chips greatly limits the ability to field untethered edge devices. We present the NV-1, a new…
In this paper, we present two symbiotic optimizations to optimize recursive task parallel (RTP) programs by reducing the task creation and termination overheads. Our first optimization Aggressive Finish-Elimination (AFE) helps reduce the…
Existing attribute-value extraction (AVE) models require large quantities of labeled data for training. However, new products with new attribute-value pairs enter the market every day in real-world e-Commerce. Thus, we formulate AVE in…
The problem of super-resolution compressive sensing (SR-CS) is crucial for various wireless sensing and communication applications. Existing methods often suffer from limited resolution capabilities and sensitivity to hyper-parameters,…
The Fast Fourier Transform(FFT) is a classic signal processing algorithm that is utilized in a wide range of applications. For image processing, FFT computes on every pixel's value of an image, regardless of their properties in frequency…
With the rapid growth of mobile robotics and embedded intelligence, there is an increasing demand for efficient on-device data processing on edge platforms. A promising research direction is the use of neuromorphic sensors inspired by human…
This paper proposes a novel user-defined keyword spotting framework that accurately detects audio keywords based on text enrollment. Since audio data possesses additional acoustic information compared to text, there are discrepancies…
High-density biosignal recordings are critical for neural decoding and clinical monitoring, yet real-world deployments often rely on low-density (LD) montages due to hardware and operational constraints. This motivates spatial…
Voice-enabled commercial products are ubiquitous, typically enabled by lightweight on-device keyword spotting (KWS) and full automatic speech recognition (ASR) in the cloud. ASR systems require significant computational resources in…
To satisfy the expected plethora of computation-heavy applications, federated edge learning (FEEL) is a new paradigm featuring distributed learning to carry the capacities of low-latency and privacy-preserving. To further improve the…
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pareto front of model accuracy vs model size, researchers are…