{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:19:48Z","timestamp":1781194788530,"version":"3.54.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413522","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"850-854","source":"Crossref","is-referenced-by-count":22,"title":["Subspectral Normalization for Neural Audio Data Processing"],"prefix":"10.1109","author":[{"given":"Simyung","family":"Chang","sequence":"first","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyoungwoo","family":"Park","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janghoon","family":"Cho","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyunsin","family":"Park","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungrack","family":"Yun","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyuwoong","family":"Hwang","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683288"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053274"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1766"},{"key":"ref13","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref14","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref15","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref17","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","author":"mesaros","year":"2018","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018)"},{"key":"ref19","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"949","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint ctc-attention based end-to-end speech recognition with a deep cnn encoder and rnn- lm","author":"hori","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902732"},{"key":"ref20","article-title":"Edgespeechnets: Highly efficient deep neural networks for speech recognition on the edge","author":"lin","year":"2018"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413522.pdf?arnumber=9413522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:17:59Z","timestamp":1659485879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413522","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}