Demo Abstract: In-Ear-Voice - Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms

Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation Pub Date : 2023-05-09 DOI:10.1145/3576842.3589166

Philipp Schilk, Niccolò Polvani, Andrea Ronco, M. Cernak, M. Magno

{"title":"Demo Abstract: In-Ear-Voice - Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms","authors":"Philipp Schilk, Niccolò Polvani, Andrea Ronco, M. Cernak, M. Magno","doi":"10.1145/3576842.3589166","DOIUrl":null,"url":null,"abstract":"This demonstration presents a custom-developed research platform for low-power wireless earbuds based on the cutting-edge Ambiq Apollo 4 Blue SoC, and targeted at applications in in-ear sensing and on-the-edge data processing. The earbud shown is currently equipped with a novel, commercial MEMS bone-conduction microphone. Such microphones can record the wearer’s speech with much greater isolation, enabling personalized voice activity detection and further audio enhancement applications. The device is running a specialized, TinyML-based, voice activity detection algorithm, indicating the wearer’s speech using an onboard LED. A second identical earbud attempts to do the same detection using a traditional air-conduction microphone is also shown to underline the advantage the bone-conduction microphone provides. Overall the platform achieves 2.64mW average power consumption at 14uJ per inference, reaching 43h of battery life on a miniature 32mAh li-ion cell without duty cycling.","PeriodicalId":266438,"journal":{"name":"Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3576842.3589166","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

This demonstration presents a custom-developed research platform for low-power wireless earbuds based on the cutting-edge Ambiq Apollo 4 Blue SoC, and targeted at applications in in-ear sensing and on-the-edge data processing. The earbud shown is currently equipped with a novel, commercial MEMS bone-conduction microphone. Such microphones can record the wearer’s speech with much greater isolation, enabling personalized voice activity detection and further audio enhancement applications. The device is running a specialized, TinyML-based, voice activity detection algorithm, indicating the wearer’s speech using an onboard LED. A second identical earbud attempts to do the same detection using a traditional air-conduction microphone is also shown to underline the advantage the bone-conduction microphone provides. Overall the platform achieves 2.64mW average power consumption at 14uJ per inference, reaching 43h of battery life on a miniature 32mAh li-ion cell without duty cycling.

查看原文本刊更多论文

摘要:入耳式语音——用于入耳式传感平台的骨传导麦克风的毫瓦音频增强

本次演示展示了一个定制开发的低功耗无线耳塞研究平台，该平台基于尖端的Ambiq Apollo 4 Blue SoC，针对入耳式传感和边缘数据处理的应用。所示的耳机目前配备了一种新颖的商用MEMS骨传导麦克风。这种麦克风可以以更高的隔离度记录佩戴者的语音，从而实现个性化的语音活动检测和进一步的音频增强应用。该设备运行一种专门的、基于tinyml的语音活动检测算法，通过板载LED指示佩戴者的语音。第二个相同的耳塞尝试使用传统的空气传导麦克风进行相同的检测，也显示了骨传导麦克风提供的优势。总体而言，该平台在每推理14uJ时实现2.64mW的平均功耗，在无占空比的微型32mAh锂离子电池上达到43h的电池寿命。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation

自引率

0.00%

发文量