@inproceedings{ce627d33dbe94928b6afd211b84cab3b,
title = "ERSAM: Neural Architecture Search for Energy-Efficient and Real-Time Social Ambiance Measurement",
abstract = "Social ambiance describes the context in which social interactions happen, and can be measured using speech audio by counting the number of concurrent speakers. This measurement has enabled various mental health tracking and human-centric IoT applications. While on-device Socal Ambiance Measure (SAM) is highly desirable to ensure user privacy and thus facilitate wide adoption of the aforementioned applications, the required computational complexity of state-of-the-art deep neural networks (DNNs) powered SAM solutions stands at odds with the often constrained resources on mobile devices. Furthermore, only limited labeled data is available or practical when it comes to SAM under clinical settings due to various privacy constraints and the required human effort, further challenging the achievable accuracy of on-device SAM solutions. To this end, we propose a dedicated neural architecture search framework for Energy-efficient and Real-time SAM (ERSAM). Specifically, our ERSAM framework can automatically search for DNNs that push forward the achievable accuracy vs. hardware efficiency frontier of mobile SAM solutions. For example, ERSAM-delivered DNNs only consume 40 mW • 12 h energy and 0.05 seconds processing latency for a 5 seconds audio segment on a Pixel 3 phone, while only achieving an error rate of 14.3% on a social ambiance dataset generated by LibriSpeech. We can expect that our ERSAM framework can pave the way for ubiquitous on-device SAM solutions which are in growing demand.",
keywords = "neural arch search, social ambiance",
author = "Chaojian Li and Wenwan Chen and Jiayi Yuan and Lin, {Yingyan Celine} and Ashutosh Sabharwal",
note = "Funding Information: ∗Equal contribution. We would like to acknowledge the funding support from the NSF SCH, Expedition, and RTML programs (Award ID: 1838873, 1730574, and 1937592) for this project. Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",
year = "2023",
doi = "10.1109/ICASSP49357.2023.10095360",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings",
address = "United States",
}