{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T18:08:48Z","timestamp":1776362928973,"version":"3.51.2"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053609","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"66-70","source":"Crossref","is-referenced-by-count":52,"title":["Weakly-Supervised Sound Event Detection with Self-Attention"],"prefix":"10.1109","author":[{"given":"Koichi","family":"Miyazaki","sequence":"first","affiliation":[]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[]},{"given":"Kazuya","family":"Takeda","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2895254"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.06.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2858559"},{"key":"ref15","article-title":"Attention-based deep multiple instance learning","author":"ilse","year":"2018"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref18","first-page":"5884","article-title":"Speech-transformer: A norecurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref28","first-page":"32","article-title":"The SINS database for detection of daily activities in a home environment using an acoustic sensor network","author":"dekkers","year":"2017","journal-title":"Proc DCAS Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521669"},{"key":"ref27","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"ISMIR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref5","article-title":"Deep convolutional neural networks and data augmentation for acoustic event detection","author":"takahashi","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"ref7","first-page":"1291","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","volume":"25","author":"cak?r","year":"2017","journal-title":"IEEE\/ACM TASLP"},{"key":"ref2","first-page":"2609","article-title":"User activity estimation method based on probabilistic generative model of acoustic event sequence with user activity and its subordinate categories","volume":"2013","author":"imoto","year":"2013","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964310"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2012.6343802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref22","article-title":"Close to human quality TTS with Transformer","author":"li","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref24","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref23","article-title":"Self-attention mechanism based system for dcase2018 challenge task1 and task4","author":"wang","year":"2018","journal-title":"IEEE AASP Challenge on DCASE 2018 technical reports"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref25","article-title":"Layer normalization","author":"ba","year":"2016"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053609.pdf?arnumber=9053609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:14:47Z","timestamp":1656360887000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053609","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}