{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T06:03:21Z","timestamp":1778825001680,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,9,29]],"date-time":"2018-09-29T00:00:00Z","timestamp":1538179200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"French ANR","award":["ANR-16-CE22-0012"],"award-info":[{"award-number":["ANR-16-CE22-0012"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1186\/s13636-018-0138-4","type":"journal-article","created":{"date-parts":[[2018,9,29]],"date-time":"2018-09-29T07:17:12Z","timestamp":1538205432000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Relevance-based quantization of scattering features for unsupervised mining of environmental audio"],"prefix":"10.1186","volume":"2018","author":[{"given":"Vincent","family":"Lostanlen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gr\u00e9goire","family":"Lafay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joakim","family":"And\u00e9n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1253-4427","authenticated-orcid":false,"given":"Mathieu","family":"Lagrange","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,29]]},"reference":[{"issue":"16","key":"138_CR1","doi-asserted-by":"publisher","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","volume":"62","author":"J. And\u00e9n","year":"2014","unstructured":"J. And\u00e9n, S. Mallat, Deep scattering spectrum. IEEE Trans. Sig. Process. 62(16), 4114\u20134128 (2014).","journal-title":"IEEE Trans. Sig. Process"},{"key":"138_CR2","doi-asserted-by":"crossref","unstructured":"R. Arandjelovic, A. Zisserman, in IEEE International Conference on Computer Vision (ICCV). Look, listen and learn (IEEE, 2017), pp. 609\u2013617.","DOI":"10.1109\/ICCV.2017.73"},{"issue":"2","key":"138_CR3","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1121\/1.2750160","volume":"122","author":"J. J. Aucouturier","year":"2007","unstructured":"J. J. Aucouturier, B. Defreville, F. Pachet, The bag-of-frames approach to audio pattern recognition: A sufficient model for urban soundscapes but not for polyphonic music. J. Acoust. Soc. Am. 122(2), 881\u2013891 (2007).","journal-title":"J. Acoust. Soc. Am"},{"key":"138_CR4","first-page":"892","volume-title":"Advances in Neural Information Processing Systems","author":"Y. Aytar","year":"2016","unstructured":"Y. Aytar, C. Vondrick, A. Torralba, in Advances in Neural Information Processing Systems. Soundnet: Learning sound representations from unlabeled video (Curran Associates, Inc.Red Hook, 2016), pp. 892\u2013900."},{"key":"138_CR5","doi-asserted-by":"publisher","first-page":"6445","DOI":"10.1109\/ICASSP.2016.7472918","volume-title":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"V. Bisot","year":"2016","unstructured":"V. Bisot, R. Serizel, S. Essid, G. Richard, in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Acoustic scene classification with matrix factorization for unsupervised feature learning (IEEENew York, 2016), pp. 6445\u20136449."},{"issue":"4","key":"138_CR6","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/TBME.2013.2294324","volume":"61","author":"V. Chud\u00e1\u010dek","year":"2013","unstructured":"V. Chud\u00e1\u010dek, J. Anden, S. Mallat, P. Abry, M. Doret, Scattering transform for intrapartum fetal heart rate variability fractal analysis: A case study. IEEE Trans. Biomed. Eng. 61(4), 1100\u20131108 (2013).","journal-title":"IEEE Trans. Biomed. Eng"},{"issue":"4","key":"138_CR7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. Davis","year":"1980","unstructured":"S. Davis, P. Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Sig. Process. 28(4), 357\u2013366 (1980).","journal-title":"IEEE Trans. Acoust. Speech Sig. Process"},{"issue":"1","key":"138_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. P. Dempster","year":"1977","unstructured":"A. P. Dempster, N. M. Laird, D. B. Rubin, Maximum likelihood from incomplete data via the EM algorithm. J. Royal Stat. Soc. B Stat. Methol. 39(1), 1\u201338 (1977).","journal-title":"J. Royal Stat. Soc. B Stat. Methol"},{"issue":"6","key":"138_CR9","first-page":"865","volume":"92","author":"D. Dubois","year":"2006","unstructured":"D. Dubois, C. Guastavino, M. Raimbault, A cognitive approach to urban soundscapes: Using verbal data to access everyday life auditory categories. Acta Acustica U. Acustica. 92(6), 865\u2013874 (2006).","journal-title":"Acta Acustica U. Acustica"},{"key":"138_CR10","unstructured":"J. R. Gloaguen, A. Can, M. Lagrange, J. F. Petiot, in Workshop on Detection and Classification of Acoustic Scenes and Events. Estimating traffic noise levels using acoustic monitoring: A preliminary study, (2016)."},{"key":"138_CR11","unstructured":"F. Guyot, S. Nathanail, F. Montignies, B. Masson, in Proceedings Forum Acusticum. Urban sound environment quality through a physical and perceptive classification of sound sources: A cross-cultural study (Budapest, Hungary, 2005)."},{"key":"138_CR12","volume-title":"A practical guide to support vector classification. Tech. rep.","author":"C. W. Hsu","year":"2003","unstructured":"C. W. Hsu, C. C. Chang, C. J. Lin, et al., A practical guide to support vector classification. Tech. rep. (National Taiwan University, Taipei, 2003)."},{"key":"138_CR13","doi-asserted-by":"crossref","unstructured":"J. Kang, Urban sound environment (CRC Press, 2006).","DOI":"10.1201\/9781482265613"},{"key":"138_CR14","doi-asserted-by":"crossref","unstructured":"S Kuwano, S Namba, T Kato, J Hellbrck, Memory of the loudness of sounds in relation to overall impression. Acoust. Sci. Technics. 4(24) (2003). The Acoustical Society of Japan.","DOI":"10.1250\/ast.24.194"},{"issue":"5","key":"138_CR15","first-page":"487","volume":"138","author":"M. Lagrange","year":"2015","unstructured":"M. Lagrange, G. Lafay, B. Defreville, J. J. Aucouturier, The bag-of-frames approach: A not so sufficient model for urban soundscapes. JASA Express Lett. 138(5), 487\u2013492 (2015).","journal-title":"JASA Express Lett"},{"issue":"6","key":"138_CR16","first-page":"912","volume":"92","author":"C. Lavandier","year":"2006","unstructured":"C. Lavandier, B. Defr\u00e9ville, The contribution of sound source characteristics in the assessment of urban soundscapes. Acta Acustica U. Acustica. 92(6), 912\u2013921 (2006). Stuttgart, Germany.","journal-title":"Acta Acustica U. Acustica"},{"key":"138_CR17","unstructured":"H. Lee, P. Pham, Y. Largman, A. Ng, in Proc. NIPS. Unsupervised feature learning for audio classification using convolutional deep belief networks, (2009), pp. 1096\u20131104."},{"issue":"2","key":"138_CR18","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S. Lloyd","year":"1982","unstructured":"S. Lloyd, Least squares quantization in PCM. IEEE Trans. Inf. Theory. 28(2), 129\u2013137 (1982).","journal-title":"IEEE Trans. Inf. Theory"},{"key":"138_CR19","unstructured":"B. Logan, in Proceedings of the International Symposium on Music Information Retrieval. Mel frequency cepstral coefficients for music modeling, (2000)."},{"key":"138_CR20","volume-title":"Convolutional operators in the time-frequency domain. Ph.D. thesis","author":"V. Lostanlen","year":"2017","unstructured":"V. Lostanlen, Convolutional operators in the time-frequency domain. Ph.D. thesis (\u00c9cole Normale Sup\u00e9rieure, Paris, 2017)."},{"key":"138_CR21","unstructured":"V. Lostanlen, C. E. Cella, in Proceedings of the International Society for Music Information Retrieval Conference. ISMIR. Deep convolutional networks in the pitch spiral for music instrument classification, (2016)."},{"issue":"10","key":"138_CR22","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1002\/cpa.21413","volume":"65","author":"S. Mallat","year":"2012","unstructured":"S. Mallat, Group Invariant Scattering. Commun. Pur. Appl. Math. 65(10), 1331\u20131398 (2012). Wiley, New York.","journal-title":"Commun. Pur. Appl. Math"},{"issue":"4","key":"138_CR23","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/nn.3347","volume":"16","author":"J. H. McDermott","year":"2013","unstructured":"J. H. McDermott, M. Schemitsch, E. P. Simoncelli, Summary statistics in auditory perception. Nat. Neurosci. 16(4), 493\u2013498 (2013).","journal-title":"Nat. Neurosci"},{"issue":"6","key":"138_CR24","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/79.543975","volume":"13","author":"T. K. Moon","year":"1996","unstructured":"T. K. Moon, The expectation-maximization algorithm. IEEE Signal Proc. Mag. 13(6), 47\u201360 (1996). New York.","journal-title":"IEEE Signal Proc. Mag"},{"issue":"4","key":"138_CR25","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.conb.2004.06.005","volume":"14","author":"I. Nelken","year":"2004","unstructured":"I. Nelken, Processing of complex stimuli and natural scenes in the auditory cortex. Curr. Opin. Neurobiol. 14(4), 474\u2013480 (2004). Elsevier, Amsterdam.","journal-title":"Curr. Opin. Neurobiol"},{"issue":"4","key":"138_CR26","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1038\/nn.3360","volume":"16","author":"I. Nelken","year":"2013","unstructured":"I. Nelken, A. de Cheveign\u00e9, An ear for statistics. Nat. Neurosci. 16(4), 381\u2013382 (2013).","journal-title":"Nat. Neurosci"},{"key":"138_CR27","unstructured":"S. R. Ness, H. Symonds, P. Spong, G. Tzanetakis, The Orchive: Data mining a massive bioacoustic archive. Int. Work. Mach. Learn. Bioacoustics (2013)."},{"key":"138_CR28","doi-asserted-by":"crossref","unstructured":"O. Pele, M. Werman, in European Conference on Computer Vision. A linear time histogram metric for improved SIFT matching (Springer, 2008), pp. 495\u2013508.","DOI":"10.1007\/978-3-540-88690-7_37"},{"issue":"4","key":"138_CR29","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1121\/1.4929747","volume":"138","author":"P. Ricciardi","year":"2015","unstructured":"P. Ricciardi, P. Delaitre, C. Lavandier, F. Torchia, P. Aumond, Sound quality indicators for urban places in Paris cross-validated by Milan data. J. Acoust. Soc. Am. 138(4), 2337\u20132348 (2015).","journal-title":"J. Acoust. Soc. Am"},{"key":"138_CR30","doi-asserted-by":"crossref","unstructured":"T. Sainath, R. J. Weiss, A. Senior, K. W. Wilson, O. Vinyals, in Proceedings of INTERSPEECH. Learning the speech front-end with raw waveform cldnns, (2015).","DOI":"10.21437\/Interspeech.2015-1"},{"issue":"7079","key":"138_CR31","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1038\/nature04485","volume":"439","author":"E. C. Smith","year":"2006","unstructured":"E. C. Smith, M. S. Lewicki, Efficient auditory coding. Nature. 439(7079), 978\u2013982 (2006).","journal-title":"Nature"},{"issue":"10","key":"138_CR32","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","volume":"17","author":"D. Stowell","year":"2015","unstructured":"D. Stowell, D. Giannoulis, E. Benetos, M. Lagrange, M. D. Plumbley, Detection and classification of acoustic scenes and events. IEEE Trans. Multimed. 17(10), 1733\u20131746 (2015).","journal-title":"IEEE Trans. Multimed"},{"key":"138_CR33","unstructured":"D. Stowell, M. D. Plumbley, Large-scale analysis of frequency modulation in birdsong databases. Methods Ecol. Evol. 11: (2013). New York."},{"issue":"3","key":"138_CR34","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/s12304-015-9248-x","volume":"8","author":"J. Sueur","year":"2015","unstructured":"J. Sueur, A. Farina, Ecoacoustics: the ecological investigation and interpretation of environmental sound. Biosemiotics. 8(3), 493\u2013502 (2015). Berlin.","journal-title":"Biosemiotics"},{"key":"138_CR35","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1016\/j.sigpro.2013.07.029","volume":"94","author":"A. Venkitaraman","year":"2014","unstructured":"A. Venkitaraman, A. Adiga, C. S. Seelamantula, Auditory-motivated Gammatone wavelet transform. Sig. Process. 94:, 608\u2013619 (2014).","journal-title":"Sig. Process"},{"key":"138_CR36","first-page":"143","volume-title":"Proc. SampTA","author":"I. Waldspurger","year":"2017","unstructured":"I. Waldspurger, in Proc. SampTA. Exponential decay of scattering coefficients (IEEENew York, 2017), pp. 143\u2013146. Conference was held in Tallinn, Estonia."},{"issue":"3","key":"138_CR37","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/j.anbehav.2005.07.014","volume":"71","author":"P. S. Warren","year":"2006","unstructured":"P. S. Warren, M. Katti, M. Ermann, A. Brazel, Urban bioacoustics: It\u2019s not just noise. Anim. Behav. 71(3), 491\u2013502 (2006).","journal-title":"Anim. Behav"},{"issue":"6","key":"138_CR38","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1890\/12-2088.1","volume":"23","author":"J. Wimmer","year":"2013","unstructured":"J. Wimmer, M. Towsey, P. Roe, I. Williamson, Sampling environmental acoustic recordings to determine bird species richness. Ecol. Appl. 23(6), 1419\u20131428 (2013).","journal-title":"Ecol. Appl"},{"key":"138_CR39","first-page":"1601","volume-title":"Advances in Neural Information Processing Systems. (NIPS) No. 17","author":"L. Zelnik-Manor","year":"2004","unstructured":"L. Zelnik-Manor, P. Perona, in Advances in Neural Information Processing Systems. (NIPS) No. 17. Self-tuning spectral clustering (MIT PressCambridge, 2004), pp. 1601\u20131608."},{"key":"138_CR40","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.ecoinf.2016.05.005","volume":"34","author":"L. Zhang","year":"2016","unstructured":"L. Zhang, M. Towsey, J. Zhang, P. Roe, Classifying and ranking audio clips to support bird species richness surveys. Ecol. Inform. 34:, 108\u2013116 (2016).","journal-title":"Ecol. Inform"},{"key":"138_CR41","unstructured":"E. Zwicker, H. Fastl, Psychoacoustics: Facts and models, vol. 22 (Springer Science & Business Media, 2013)."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-018-0138-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-018-0138-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-018-0138-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T22:01:37Z","timestamp":1720648897000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-018-0138-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,29]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["138"],"URL":"https:\/\/doi.org\/10.1186\/s13636-018-0138-4","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,29]]},"assertion":[{"value":"23 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"15"}}