{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:23:53Z","timestamp":1763202233550,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T00:00:00Z","timestamp":1555372800000},"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":[[2019,4,16]]},"DOI":"10.1145\/3302506.3310398","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"169-180","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":43,"title":["Mic2Mic"],"prefix":"10.1145","author":[{"given":"Akhil","family":"Mathur","sequence":"first","affiliation":[{"name":"University College London"}]},{"given":"Anton","family":"Isopoussu","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs"}]},{"given":"Fahim","family":"Kawsar","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs"}]},{"given":"Nadia","family":"Berthouze","sequence":"additional","affiliation":[{"name":"University College London"}]},{"given":"Nicholas D.","family":"Lane","sequence":"additional","affiliation":[{"name":"University of Oxford"}]}],"member":"320","published-online":{"date-parts":[[2019,4,16]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2015. Alexa API. https:\/\/developer.amazon.com\/docs\/alexa-voice-service\/api-overview.html. (2015)."},{"key":"e_1_3_2_1_2_1","unstructured":"2015. Google Speech API. https:\/\/cloud.google.com\/speech\/. (2015)."},{"key":"e_1_3_2_1_3_1","unstructured":"2015. Speech Commands Dataset. https:\/\/research.googleblog.com\/2017\/08\/launching-speech-commands-dataset.html. (2015)."},{"key":"e_1_3_2_1_4_1","unstructured":"2017. Mozilla DeepSpeech2. https:\/\/hacks.mozilla.org\/2017\/11\/a-journey-to-10--word-error-rate\/. (2017)."},{"key":"e_1_3_2_1_5_1","volume-title":"How To Do Good Research In Activity Recognition. Workshop in conjunction with Pervasive.","author":"Amft OD","year":"2010","unstructured":"OD Amft. 2010. On the need for quality standards in activity recognition using ubiquitous sensors. In How To Do Good Research In Activity Recognition. Workshop in conjunction with Pervasive."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/11551201_4"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCTHEALTH.2006.361624"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2994551.2994564"},{"key":"e_1_3_2_1_11_1","volume-title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. arXiv preprint arXiv:1711.09020","author":"Choi Yunjey","year":"2017","unstructured":"Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. 2017. StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. arXiv preprint arXiv:1711.09020 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"Synthesizing Audio with Generative Adversarial Networks. arXiv preprint arXiv:1802.04208","author":"Donahue Chris","year":"2018","unstructured":"Chris Donahue, Julian McAuley, and Miller Puckette. 2018. Synthesizing Audio with Generative Adversarial Networks. arXiv preprint arXiv:1802.04208 (2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2494091.2499576"},{"key":"e_1_3_2_1_16_1","unstructured":"Das A. et al. 2014. Fingerprinting Smart Devices Through Embedded Acoustic Components. arXiv preprint arXiv:1403.3366 (2014)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2462456.2465426"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Mathur A. et al. 2018. Using Deep Data Augmentation Training to Address Software and Hardware Heterogeneities in Wearable and Smartphone Sensing Devices. In IPSN. IEEE. 10.1109\/IPSN.2018.00048","DOI":"10.1109\/IPSN.2018.00048"},{"key":"e_1_3_2_1_19_1","volume-title":"SEGAN: Speech enhancement generative adversarial network. arXiv preprint arXiv:1703.09452","author":"Pascual S.","year":"2017","unstructured":"Pascual S. et al. 2017. SEGAN: Speech enhancement generative adversarial network. arXiv preprint arXiv:1703.09452 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809718"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_25_1","volume-title":"Environmental noise embeddings for robust speech recognition. arXiv preprint arXiv:1601.02553","author":"Kim Suyoun","year":"2016","unstructured":"Suyoun Kim, Bhiksha Raj, and Ian Lane. 2016. Environmental noise embeddings for robust speech recognition. arXiv preprint arXiv:1601.02553 (2016)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2804262"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Bo Li Tara Sainath Arun Narayanan Joe Caroselli Michiel Bacchiani Ananya Misra Izhak Shafran Hasim Sak Golan Pundak Kean Chin et al. 2017. Acoustic modeling for google home. (2017).","DOI":"10.21437\/Interspeech.2017-234"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"D. Liang Z. Huang and Z. C. Lipton. 2018. Learning Noise-Invariant Representations for Robust Speech Recognition. ArXiv e-prints (July 2018). arXiv:1807.06610","DOI":"10.1109\/SLT.2018.8639575"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163086"},{"key":"e_1_3_2_1_30_1","volume-title":"Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks. arXiv preprint arXiv:1705.01908","author":"Liu Yifan","year":"2017","unstructured":"Yifan Liu, Zengchang Qin, Zhenbo Luo, and Hua Wang. 2017. Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks. arXiv preprint arXiv:1705.01908 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869983.1869992"},{"key":"e_1_3_2_1_32_1","unstructured":"Xugang Lu Yu Tsao Shigeki Matsuda and Chiori Hori. 2013. Speech enhancement based on deep denoising autoencoder."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-6"},{"key":"e_1_3_2_1_34_1","volume-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification. arXiv preprint arXiv:1709.01703","author":"Michelsanti Daniel","year":"2017","unstructured":"Daniel Michelsanti and Zheng-Hua Tan. 2017. Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification. arXiv preprint arXiv:1709.01703 (2017)."},{"volume-title":"Librispeech: an ASR corpus based on public domain audio books","author":"Panayotov Vassil","key":"e_1_3_2_1_35_1","unstructured":"Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. Librispeech: an ASR corpus based on public domain audio books. In ICASSP. IEEE, 5206--5210."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832988"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"e_1_3_2_1_40_1","volume-title":"Invariant representations for noisy speech recognition. arXiv preprint arXiv:1612.01928","author":"Serdyuk Dmitriy","year":"2016","unstructured":"Dmitriy Serdyuk, Kartik Audhkhasi, Phil\u00e9mon Brakel, Bhuvana Ramabhadran, Samuel Thomas, and Yoshua Bengio. 2016. Invariant representations for noisy speech recognition. arXiv preprint arXiv:1612.01928 (2016)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517351.2517362"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493435"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"e_1_3_2_1_44_1","volume-title":"Hello edge: Keyword spotting on microcontrollers. arXiv preprint arXiv:1711.07128","author":"Zhang Yundong","year":"2017","unstructured":"Yundong Zhang, Naveen Suda, Liangzhen Lai, and Vikas Chandra. 2017. Hello edge: Keyword spotting on microcontrollers. arXiv preprint arXiv:1711.07128 (2017)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"IPSN '19: The 18th International Conference on Information Processing in Sensor Networks","sponsor":["SIGBED ACM Special Interest Group on Embedded Systems","IEEE-SPS Signal Processing Society"],"location":"Montreal Quebec Canada","acronym":"IPSN '19"},"container-title":["Proceedings of the 18th International Conference on Information Processing in Sensor Networks"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302506.3310398","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3302506.3310398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:25:38Z","timestamp":1750206338000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3302506.3310398"}},"subtitle":["using cycle-consistent generative adversarial networks to overcome microphone variability in speech systems"],"short-title":[],"issued":{"date-parts":[[2019,4,16]]},"references-count":45,"alternative-id":["10.1145\/3302506.3310398","10.1145\/3302506"],"URL":"https:\/\/doi.org\/10.1145\/3302506.3310398","relation":{},"subject":[],"published":{"date-parts":[[2019,4,16]]},"assertion":[{"value":"2019-04-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}