paper-with-me

홈 › Papers

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

2024-02-20 · Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra

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.

📄 PDF Abstract BibTeX arXiv:2402.13076

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

SimulTron: On-Device Simultaneous Speech to Speech Translation

2024-06-04 · Alex Agranovich, Eliya Nachmani, Oleg Rybakov, Yifan Ding 외

Simultaneous speech-to-speech translation (S2ST) holds the promise of breaking down communication barriers and enabling fluid conversations across languages. However, achieving accurate, real-time translation through mob…

Simultaneous Speech-to-Speech TranslationSpeech-to-Speech TranslationTranslation

A Low-Power Streaming Speech Enhancement Accelerator For Edge Devices

2025-03-27 · Ci-Hao Wu, Tian-Sheuan Chang

Transformer-based speech enhancement models yield impressive results. However, their heterogeneous and complex structure restricts model compression potential, resulting in greater complexity and reduced hardware efficie…

Model CompressionSpeech Enhancement

Large Model Empowered Streaming Speech Semantic Communications

2025-01-10 · Zhenzi Weng, Zhijin Qin, Geoffrey Ye Li

In this paper, we introduce a large model-empowered streaming semantic communication system for speech transmission across various languages, named LSSC-ST. Specifically, we devise an edge-device collaborative semantic c…

modelSemantic CommunicationTranslation

Breaking the Programming Language Barrier: Multilingual Prompting to Empower Non-Native English Learners

2024-12-17 · James Prather, Brent N. Reeves, Paul Denny, Juho Leinonen 외

Non-native English speakers (NNES) face multiple barriers to learning programming. These barriers can be obvious, such as the fact that programming language syntax and instruction are often in English, or more subtle, su…

Code Generation

MPEG-H Audio for Improving Accessibility in Broadcasting and Streaming

2019-09-25

Broadcasting and streaming services still suffer from various levels of accessibility barriers for a significant portion of the population, limiting the access to information and culture, and in the most severe cases lim…

Cultural Vocal Bursts Intensity Prediction