{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T18:53:53Z","timestamp":1768071233474,"version":"3.49.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683727","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"925-929","source":"Crossref","is-referenced-by-count":15,"title":["Acoustic Scene Generation with Conditional Samplernn"],"prefix":"10.1109","author":[{"given":"Qiuqiang","family":"Kong","sequence":"first","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent AI lab, Bellevue, USA"}]},{"given":"Turab","family":"Iqbal","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"}]},{"given":"Yin","family":"Cao","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1121"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"ref13","article-title":"A note on the evaluation of generative models","author":"theis","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref14","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref17","article-title":"DCASE 2018 Challenge baseline with convolutional neural networks","author":"kong","year":"2018","journal-title":"DCAS Workshop"},{"key":"ref18","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref6","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref5","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"IEE Workshop on Speech Synthesis"},{"key":"ref8","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den a\u00e4ron","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"1747","article-title":"Pixel recurrent neural networks","volume":"48","author":"oord","year":"2016","journal-title":"Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1944745.1944755"},{"key":"ref9","first-page":"1929","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683727.pdf?arnumber=8683727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:33:42Z","timestamp":1753731222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683727\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683727","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}