Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909511008124928 |
|---|---|
| author | Li, Yang Shangguan, Yuan Wang, Yuhao Lai, Liangzhen Chang, Ernie Zhao, Changsheng Shi, Yangyang Chandra, Vikas |
| author_facet | Li, Yang Shangguan, Yuan Wang, Yuhao Lai, Liangzhen Chang, Ernie Zhao, Changsheng Shi, Yangyang Chandra, Vikas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13076 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions Li, Yang Shangguan, Yuan Wang, Yuhao Lai, Liangzhen Chang, Ernie Zhao, Changsheng Shi, Yangyang Chandra, Vikas Sound Machine Learning Audio and Speech Processing 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. |
| title | Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.13076 |