paper-with-me

Papers

KWT-Tiny: RISC-V Accelerated, Embedded Keyword Spotting Transformer

2024-07-22 · Aness Al-Qawlaq, Ajay Kumar M, Deepu John

This paper explores the adaptation of Transformerbased models for edge devices through the quantisation and hardware acceleration of the ARM Keyword Transformer (KWT) model on a RISC-V platform. The model was targeted to run on 64kB RAM in bare-metal C using a custom-developed edge AI library. KWT-1 was retrained to be 369 times smaller, with only a 10% loss in accuracy through reducing output classes from 35 to 2. The retraining and quantisation reduced model size from 2.42 MB to 1.65 kB. The integration of custom RISC-V instructions that accelerated GELU and SoftMax operations enabled a 5x speedup and thus ~5x power reduction in inference, with inference clock cycle counts decreasing from 26 million to 5.5 million clock cycles while incurring a small area overhead of approximately 29%. The results demonstrate a viable method for porting and accelerating Transformer-based models in low-power IoT devices.

📄 PDF Abstract BibTeX arXiv:2407.16026

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword Spotting

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers

2023-05-30 · Davide Nadalini, Manuele Rusci, Luca Benini, Francesco Conti

Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications. This pap…

Continual Learningimage-classificationImage ClassificationKeyword Spotting

Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)

2025-09-05 · Abhishek Dey, Saurabh Srivastava, Gaurav Singh, Robert G. Pettit arxiv

This paper presents PICO-TINYML-BENCHMARK, a modular and platform-agnostic framework for benchmarking the real-time performance of TinyML models on resource-constrained embedded systems. Evaluating key metrics such as in…

Keyword Spotting

Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices

2025-08-06 · Yael Segal-Feldman, Ann R. Bradlow, Matthew Goldrick, Joseph Keshet arxiv

Open-vocabulary keyword spotting (KWS) refers to the task of detecting words or terms within speech recordings, regardless of whether they were included in the training data. This paper introduces an open-vocabulary keyw…

Keyword Spotting

Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications

2025-07-21 · Yujia Shi, Emil Njor, Pablo Martínez-Nuevo, Sven Ewan Shepstone 외 arxiv

The success of Machine Learning is increasingly tempered by its significant resource footprint, driving interest in efficient paradigms like TinyML. However, the inherent complexity of designing TinyML systems hampers th…

Neural Architecture SearchKeyword Spotting

Prototypical Metric Transfer Learning for Continuous Speech Keyword Spotting With Limited Training Data

2019-01-12 · Harshita Seth, Pulkit Kumar, Muktabh Mayank Srivastava

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 Spottin…

General Classificationimbalanced classificationKeyword SpottingTransfer Learning