{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T06:34:05Z","timestamp":1770359645082,"version":"3.49.0"},"reference-count":28,"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\/icassp40776.2020.9053921","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"96-100","source":"Crossref","is-referenced-by-count":48,"title":["Improving Universal Sound Separation Using Sound Classification"],"prefix":"10.1109","author":[{"given":"Efthymios","family":"Tzinis","sequence":"first","affiliation":[]},{"given":"Scott","family":"Wisdom","sequence":"additional","affiliation":[]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[]},{"given":"Aren","family":"Jansen","sequence":"additional","affiliation":[]},{"given":"Daniel P. W.","family":"Ellis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Exponential family embeddings","author":"rudolph","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref13","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref15","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Chive: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","author":"kenter","year":"2019","journal-title":"Proc ICML"},{"key":"ref17","article-title":"Speaker diarization using deep recurrent convolutional neural networks for speaker embeddings","author":"cyrta","year":"2017","journal-title":"International Conference on Information Systems Architecture and Technology"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2326"},{"key":"ref28","article-title":"SDR–half-baked or well done?","author":"le roux","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref6","article-title":"Voicefilter: Targeted voice separation by speaker-conditioned spectrogram masking","author":"wang","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref20","article-title":"Audio query-based music source separation","author":"lee","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref22","article-title":"AudioSet: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2307\/2527498"},{"key":"ref23","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref26","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"0"},{"key":"ref25","year":"0"}],"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\/09053921.pdf?arnumber=9053921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:19:12Z","timestamp":1656375552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053921","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}