Related papers: Hardware Aware Training for Efficient Keyword Spot…

This paper introduces DeltaKWS, to the best of our knowledge, the first $\Delta$RNN-enabled fine-grained temporal sparsity-aware KWS IC for voice-controlled devices. The 65 nm prototype chip features a number of techniques to enhance…

Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware training (LAT)…

Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing. Although CNN hardware accelerators are already included as part of many SoC…

End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems. This simplification…

Reducing energy consumption is a pressing issue in low-power machine-type communication (MTC) networks. In this regard, the Wake-up Signal (WuS) technology, which aims to minimize the energy consumed by the radio interface of the…

Continuous Speech Keyword Spotting (CSKS) is the problem of spotting keywords in recorded conversations, when a small number of instances of keywords are available in training data. Unlike the more common Keyword Spotting, where an…

This paper introduces the system submitted by the Yidun NISP team to the video keyword wakeup challenge. We propose a mandarin keyword spotting system (KWS) with several novel and effective improvements, including a big backbone (B) model,…

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity.Since for those systems it is often required to operate both in real-time and with…

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous use of CNNs for inference is their relatively high memory…

Pruning is a neural network optimization technique that sacrifices accuracy in exchange for lower computational requirements. Pruning has been useful when working with extremely constrained environments in tinyML. Unfortunately, special…

Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed…

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. Many techniques have evolved over the past decade that made models lighter, faster, and…

Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

We propose using cascaded classifiers for a keyword spotting (KWS) task on narrow-band (NB), 8kHz audio acquired in non-IID environments -- a more challenging task than most state-of-the-art KWS systems face. We present a model that…

Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking neural networks (SNNs) share the goal of enhancing…

Recent advances in Neural Architecture Search (NAS) which extract specialized hardware-aware configurations (a.k.a. "sub-networks") from a hardware-agnostic "super-network" have become increasingly popular. While considerable effort has…

Hardware-aware Neural Architecture Search (HW-NAS) is a technique used to automatically design the architecture of a neural network for a specific task and target hardware. However, evaluating the performance of candidate architectures is a…

Accelerating Human Action Recognition (HAR) efficiently for real-time surveillance and robotic systems on edge chips remains a challenging research field, given its high computational and memory requirements. This paper proposed an…