Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions

Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang +3 more
2/20/2024
cs.SDcs.LGeess.AS

No confident code implementation found for this paper.

Abstract

Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their overall energy efficiency. We found that the influence of these parameters on power consumption varies depending on factors such as invocation frequency and memory allocation. Leveraging these insights, we propose design principles that enhance on-device speech recognition models by reducing power consumption with minimal impact on accuracy. Our approach, which adjusts model components based on their specific energy sensitivities, achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Folding Attention: Memory and Power Optimization for On-Device Transformer-based Streaming Speech Recognition

86% match2023

Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models

81% match2025

Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment

80% match2024

Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications

80% match2026

Enhancing User Experience in On-Device Machine Learning with Gated Compression Layers

79% match2024

On-device Streaming Discrete Speech Units

78% match1 repo82025

Cite this paper

@article{li2024breaking,
  title  = {Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions},
  author = {Yang Li and Yuan Shangguan and Yuhao Wang and Liangzhen Lai and Ernie Chang and Changsheng Zhao and Yangyang Shi and Vikas Chandra},
  year   = {2024},
  eprint = {2402.13076},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.13076v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.13076.svg)](https://codeofpaper.com/paper/2402.13076)

Discussion