{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:09:20Z","timestamp":1745989760882},"reference-count":12,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2024,4,1]]},"DOI":"10.1587\/transfun.2023ssl0001","type":"journal-article","created":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T22:51:19Z","timestamp":1696459879000},"page":"634-637","source":"Crossref","is-referenced-by-count":1,"title":["Noise-Robust Scream Detection Using Wave-U-Net"],"prefix":"10.1587","volume":"E107.A","author":[{"given":"Noboru","family":"HAYASAKA","sequence":"first","affiliation":[{"name":"Department of Engineering Informatics, Osaka Electro-Communication University"}]},{"given":"Riku","family":"KASAI","sequence":"additional","affiliation":[{"name":"OPTAGE Inc."}]},{"given":"Takuya","family":"FUTAGAMI","sequence":"additional","affiliation":[{"name":"Department of Engineering Informatics, Osaka Electro-Communication University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J.T. Geiger and K. Helwani, \u201cImproving event detection for audio surveillance using Gabor filterbank features,\u201d European Signal Processing Conference (EUSIPCO), pp.719-723, 2015. 10.1109\/eusipco.2015.7362476","DOI":"10.1109\/EUSIPCO.2015.7362476"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] N. Hayasaka, A. Kawamura, and N. Sasaoka, \u201cNoise-robust scream detection using band-limited spectral entropy,\u201d AEU-International Journal of Electronics and Communications, vol.76, pp.117-124, 2017. 10.1016\/j.aeue.2017.04.002","DOI":"10.1016\/j.aeue.2017.04.002"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M.K. Nandwana, A. Ziaei, and J.H.L. Hansen, \u201cRobust unsupervised detection of human screams in noisy acoustic environments,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.161-165, 2016. 10.1109\/icassp.2015.7177952","DOI":"10.1109\/ICASSP.2015.7177952"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] A. Sharma and S. Kaul, \u201cTwo-stage supervised learning-based method to detect screams and cries in urban environments,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.24, no.2, pp.290-299, 2015. 10.1109\/taslp.2015.2506264","DOI":"10.1109\/TASLP.2015.2506264"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] P. Laffitte, D. Sodoyer, C. Tatkeu, and L. Girin, \u201cDeep neural networks for automatic detection of screams and shouted speech in subway trains,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.6460-6464, 2016. 10.1109\/icassp.2016.7472921","DOI":"10.1109\/ICASSP.2016.7472921"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] T. Fukumori, \u201cDeep spectral-cepstral fusion for shouted and normal speech classification,\u201d Interspeech 2021, pp.4174-4178, Sept. 2021. 10.21437\/interspeech.2021-1245","DOI":"10.21437\/Interspeech.2021-1245"},{"key":"7","unstructured":"[7] R.C. Maher, Principles of Forensic Audio Analysis, Chapter 6, Springer, Switzerland, 2018. 10.1007\/978-3-319-99453-6"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] S. Pascual, A. Bonafonte, and J. Serr\u00e1, \u201cSEGAN: Speech enhancement generative adversarial network,\u201d arXiv:1703.09452, 2017. 10.48550\/arXiv.1703.09452","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] R. Kasai, N. Hayasaka, T. Futagami, and Y. Miyanaga, \u201cScream enhancement using Wave-U-Net,\u201d International Workshop on Smart Info-Media Systems in Asia (SISA), pp.5-8, Sept. 2021. 10.34385\/proc.66.ss1-2","DOI":"10.34385\/proc.66.SS1-2"},{"key":"10","unstructured":"[10] D. Stoller, S. Ewert, and S. Dixon, \u201cWave-U-Net: A multi-scale neural network for end-to-end audio source separation,\u201d Proc. 19th Int'l Society for Music Information Retrieval Conference (ISMIR), Sept. 2018."},{"key":"11","unstructured":"[11] Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms, European Telecommunications Standards Institute 201 108 V1.1.3, Sept. 2003."},{"key":"12","unstructured":"[12] JEIDA Noise Database (ELRA-SD37), http:\/\/universal.elra.info\/product_info.php?cPath=37_39&products_id=53"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E107.A\/4\/E107.A_2023SSL0001\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,6]],"date-time":"2024-04-06T03:27:03Z","timestamp":1712374023000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E107.A\/4\/E107.A_2023SSL0001\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,1]]},"references-count":12,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2023ssl0001","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,1]]},"article-number":"2023SSL0001"}}