{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:44:14Z","timestamp":1777164254261,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/waspaa.2017.8170052","type":"proceedings-article","created":{"date-parts":[[2017,12,13]],"date-time":"2017-12-13T14:38:44Z","timestamp":1513175924000},"page":"344-348","source":"Crossref","is-referenced-by-count":141,"title":["Scaper: A library for soundscape synthesis and augmentation"],"prefix":"10.1109","author":[{"given":"Justin","family":"Salamon","sequence":"first","affiliation":[]},{"given":"Duncan","family":"MacConnell","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Cartwright","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Li","sequence":"additional","affiliation":[]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3134664"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827516"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2037402"},{"key":"ref12","first-page":"221","author":"schwarz","year":"2011","journal-title":"State of the art in sound texture synthesis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2587218"},{"key":"ref14","first-page":"591","article-title":"JAMS: A JSON annotated music specification for reproducible MIR research","author":"humphrey","year":"2014","journal-title":"Proc 15th Int Soc Music Inf Retr Conf"},{"key":"ref15","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref16","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015","journal-title":"software available from tensorflow org"},{"key":"ref17","author":"chollet","year":"2017","journal-title":"Keras"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502229"},{"key":"ref19","author":"mcfee","year":"2017","journal-title":"librosa 0 5 0"},{"key":"ref28","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"32nd Int Conf on Machine Learning ser Proceedings of Ma-chine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540194"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref3","year":"0","journal-title":"Large-scale weakly supervised sound event detection for smart cars"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952264"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations (ICLR2015)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref7","first-page":"1097","article-title":"lmageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0166866"},{"key":"ref9","first-page":"248","article-title":"A software framework for musical data augmentation","author":"mcfee","year":"2015","journal-title":"Proc 16th Int Soc Music Inf Retr Conf"},{"key":"ref1","article-title":"The implementation of low-cost urban acoustic monitoring devices","author":"mydlarz","year":"2016","journal-title":"Applied Acoustics"},{"key":"ref20","author":"maffiolo","year":"1999","journal-title":"Semantic and acoustic characterization of urban environmental sound quality"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3347"},{"key":"ref21","first-page":"945","article-title":"The ideal urban soundscape: Investigating the sound quality of French cities","volume":"92","author":"guastavino","year":"2006","journal-title":"Acta Acustica United with Acustica"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5594\/J11396"},{"key":"ref23","article-title":"Pysox: Leveraging the audio signal processing power of sox in python","author":"bittner","year":"2016","journal-title":"17th Int Soc for Music Info Retrieval Conf Late Breaking and Demo Papers"},{"key":"ref26","article-title":"Convolutional recurrent neural networks for polyphonic sound event detection","author":"\u00e7akir","year":"2017","journal-title":"IEEE\/ACM TASLP Special Issue on Sound Scene and Event Analysis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"}],"event":{"name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY","start":{"date-parts":[[2017,10,15]]},"end":{"date-parts":[[2017,10,18]]}},"container-title":["2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8125199\/8169982\/08170052.pdf?arnumber=8170052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,17]],"date-time":"2018-01-17T18:13:22Z","timestamp":1516212802000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8170052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/waspaa.2017.8170052","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}