{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:08:32Z","timestamp":1775228912002,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,9]],"date-time":"2023-05-09T00:00:00Z","timestamp":1683590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,9]]},"DOI":"10.1145\/3576842.3582365","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T22:58:08Z","timestamp":1682549888000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-9513","authenticated-orcid":false,"given":"Philipp","family":"Schilk","sequence":"first","affiliation":[{"name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETHZ), Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0720-050X","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Polvani","sequence":"additional","affiliation":[{"name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale Lausanne (EPFL), Switzerland and Logitech Europe, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1672-8672","authenticated-orcid":false,"given":"Andrea","family":"Ronco","sequence":"additional","affiliation":[{"name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETHZ), Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5569-9491","authenticated-orcid":false,"given":"Milos","family":"Cernak","sequence":"additional","affiliation":[{"name":"Logitech Europe, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0368-8923","authenticated-orcid":false,"given":"Michele","family":"Magno","sequence":"additional","affiliation":[{"name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich (ETHZ), Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,5,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3928151"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Sebastian Braun and Ivan Tashev. 2021. On training targets for noise-robust voice activity detection. (2021). https:\/\/doi.org\/10.48550\/ARXIV.2102.07445","DOI":"10.48550\/ARXIV.2102.07445"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Christophe Chevallier. 2015. Low power design: Ramping to production. In 2015 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S). 1\u20134. https:\/\/doi.org\/10.1109\/S3S.2015.7333548","DOI":"10.1109\/S3S.2015.7333548"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Kyunghyun Cho Bart van Merrienboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. https:\/\/doi.org\/10.48550\/ARXIV.1406.1078","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662540"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3113259"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2019.8701198"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CogMI50398.2020.00025"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"David Dean Sridha Sridharan Robert Vogt and Michael Mason. 2010. The QUT-NOISE-TIMIT corpus for the evaluation of voice activity detection algorithms. https:\/\/doi.org\/10.21437\/Interspeech.2010-774","DOI":"10.21437\/Interspeech.2010-774"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054761"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Shaojin Ding Rajeev Rikhye Qiao Liang Yanzhang He Quan Wang Arun Narayanan Tom O\u2019Malley and Ian McGraw. 2022. Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2204.03793","DOI":"10.48550\/ARXIV.2204.03793"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2202.13288"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS54282.2022.9870017"},{"key":"e_1_3_2_1_15_1","volume-title":"Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William\u00a0J. Dally. 2016. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1510.00149"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. https:\/\/doi.org\/10.48550\/ARXIV.1503.02531","DOI":"10.48550\/ARXIV.1503.02531"},{"key":"e_1_3_2_1_17_1","unstructured":"Elevotec Inc. 2021. Elevoc Simultaneously-recorded Microphone\/Bone-sensor. Elevotec. https:\/\/github.com\/elevoctech\/ESMB-corpus"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.6980"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365845"},{"key":"e_1_3_2_1_20_1","volume-title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs. ArXiv abs\/1801.06601","author":"Lai Liangzhen","year":"2018","unstructured":"Liangzhen Lai, Naveen Suda, and Vikas Chandra. 2018. CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs. ArXiv abs\/1801.06601 (2018)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of The 33rd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a048)","author":"Lin Darryl","year":"2016","unstructured":"Darryl Lin, Sachin Talathi, and Sreekanth Annapureddy. 2016. Fixed Point Quantization of Deep Convolutional Networks. In Proceedings of The 33rd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a048), Maria\u00a0Florina Balcan and Kilian\u00a0Q. Weinberger (Eds.). PMLR, New York, New York, USA, 2849\u20132858. https:\/\/proceedings.mlr.press\/v48\/linb16.html"},{"key":"e_1_3_2_1_22_1","volume-title":"Enrollment-less training for personalized voice activity detection. CoRR abs\/2106.12132","author":"Makishima Naoki","year":"2021","unstructured":"Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Akihiko Takashima, Shota Orihashi, and Ryo Masumura. 2021. Enrollment-less training for personalized voice activity detection. CoRR abs\/2106.12132 (2021). arXiv:2106.12132https:\/\/arxiv.org\/abs\/2106.12132"},{"key":"e_1_3_2_1_23_1","volume-title":"Analysis of Digital Filtering with the Use of STM32 Family Microcontrollers","author":"Marciniak Tomasz","unstructured":"Tomasz Marciniak, Kacper Podbucki, Jakub Suder, and Adam D\u0105browski. 2020. Analysis of Digital Filtering with the Use of STM32 Family Microcontrollers. In Advanced, Contemporary Control, Andrzej Bartoszewicz, Jacek Kabzi\u0144ski, and Janusz Kacprzyk (Eds.). Springer International Publishing, Cham, 287\u2013295."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Flavio Martinelli Giorgia Dellaferrera Pablo Mainar and Milos Cernak. 2020. Spiking Neural Networks Trained With Backpropagation For Low Power Neuromorphic Implementation Of Voice Activity Detection. 2020 Ieee International Conference On Acoustics Speech And Signal Processing 8544\u20138548. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053412","DOI":"10.1109\/ICASSP40776.2020.9053412"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/PRIME.2018.8430328"},{"key":"e_1_3_2_1_26_1","unstructured":"NIST 2015. Evaluation Plan for the NIST Open Evaluation of Speech Activity Detection (OpenSAD15). https:\/\/www.nist.gov\/system\/files\/documents\/itl\/iad\/mig\/Open_SAD_Eval_Plan_v10.pdf"},{"key":"e_1_3_2_1_27_1","unstructured":"NIST 2015. NIST Open Speech-Activity-Detection Evaluation. https:\/\/www.nist.gov\/itl\/iad\/mig\/nist-open-speech-activity-detection-evaluation"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIPS.2009.5336254"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SAS54819.2022.9881349"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2752838"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Mark Przybocki and Martin Alvin. 2001. 2000 NIST Speaker Recognition Evaluation. NIST. https:\/\/doi.org\/10.35111\/ex24-j205","DOI":"10.35111\/ex24-j205"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDL8134"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2011.6026374"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.11.019"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/WiMob55322.2022.9941646"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3176369"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2019.8662113"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 2008 International Conference on Audio, Language, and Image Processing (01","author":"Tran Phuong","year":"2008","unstructured":"Phuong Tran, Tomasz Letowski, and Maranda McBride. 2008. Bone conduction microphone: Head sensitivity mapping for speech intelligibility and sound quality. Proceedings of the 2008 International Conference on Audio, Language, and Image Processing (01 2008), 107\u2013111."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Jean-Marc Valin. 2017. A Hybrid DSP\/Deep Learning Approach to Real-Time Full-Band Speech Enhancement. https:\/\/doi.org\/10.48550\/ARXIV.1709.08243","DOI":"10.48550\/ARXIV.1709.08243"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Jean-Marc Valin Umut Isik Neerad Phansalkar Ritwik Giri Karim Helwani and Arvindh Krishnaswamy. 2020. A Perceptually-Motivated Approach for Low-Complexity Real-Time Enhancement of Fullband Speech. https:\/\/doi.org\/10.48550\/ARXIV.2008.04259","DOI":"10.48550\/ARXIV.2008.04259"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPBDIS53214.2021.9658477"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Heming Wang Xueliang Zhang and DeLiang Wang. 2022. Attention-Based Fusion for Bone-Conducted and Air-Conducted Speech Enhancement in the Complex Domain. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 7757\u20137761. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746374","DOI":"10.1109\/ICASSP43922.2022.9746374"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-348"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310326"}],"event":{"name":"IoTDI '23: International Conference on Internet-of-Things Design and Implementation","location":"San Antonio TX USA","acronym":"IoTDI '23","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 8th ACM\/IEEE Conference on Internet of Things Design and Implementation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3576842.3582365","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3576842.3582365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:58Z","timestamp":1750183738000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3576842.3582365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,9]]},"references-count":46,"alternative-id":["10.1145\/3576842.3582365","10.1145\/3576842"],"URL":"https:\/\/doi.org\/10.1145\/3576842.3582365","relation":{},"subject":[],"published":{"date-parts":[[2023,5,9]]},"assertion":[{"value":"2023-05-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}