{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T07:07:20Z","timestamp":1768288040801,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T00:00:00Z","timestamp":1641945600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T00:00:00Z","timestamp":1641945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071302"],"award-info":[{"award-number":["62071302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701306"],"award-info":[{"award-number":["61701306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10772-022-09957-w","type":"journal-article","created":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T20:10:06Z","timestamp":1642018206000},"page":"251-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Acoustic domain mismatch compensation in bird audio detection"],"prefix":"10.1007","volume":"25","author":[{"given":"Tiantian","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0924-408X","authenticated-orcid":false,"given":"Yanhua","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaen","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,12]]},"reference":[{"key":"9957_CR1","doi-asserted-by":"crossref","unstructured":"Adavanne, S., Drossos, K., \u00c7akir, E., & Virtanen, T. (2017). Stacked convolutional and recurrent neural networks for bird audio detection. In Proc. EUSIPCO (pp. 1729\u20131733).","DOI":"10.23919\/EUSIPCO.2017.8081505"},{"key":"9957_CR2","unstructured":"Bai, J. S., Wu, R., Wang, M., et al. (2018). CIAIC-BAD sysytem for DCASE2018 challenge task3. In DCASE challenge."},{"key":"9957_CR3","unstructured":"Battenberg, E., Child, R., Coates, A., et al. (2017). Reducing bias in production speech models. CoRR, 1705, 04400."},{"key":"9957_CR4","doi-asserted-by":"crossref","unstructured":"Becker, L., Nelus, A., Gauer, J., Rudolph, L., & Martin, R. (2020). Audio feature extraction for vehicle engine noise classification. In Proc. ICASSP (pp. 711\u2013715).","DOI":"10.1109\/ICASSP40776.2020.9053117"},{"key":"9957_CR5","unstructured":"Berger, F., Freillinger, W., Primus, P., & Reisinger, W. (2018). Bird Audio Detection - DCASE 2018. In DCASE challenge"},{"key":"9957_CR6","doi-asserted-by":"crossref","unstructured":"Duan, S., Towsey, M., Zhang, J., Truskinger, A., Wimmer, J., & Roe, P. (2011). Acoustic component detection for automatic species recognition in environmental monitoring. In Proc. ISSNIP (pp. 514\u2013519).","DOI":"10.1109\/ISSNIP.2011.6146597"},{"key":"9957_CR7","unstructured":"FitzGerald, D. (2010). Harmonic\/percussive separation using median filtering. In Proc. DAFx (pp. DAFX1-DAFX-4)."},{"key":"9957_CR8","unstructured":"Franceschi, J.-Y., Fawzi, A., & Fawzi, O. (2018). Robustness of classifiers to uniform $$\\ell _p$$ and gaussian noise. In Proc. AISTATS (pp. 1\u201325)."},{"key":"9957_CR9","doi-asserted-by":"crossref","unstructured":"Grill, T., Schl\u00fcter, J. (2017). Two convolutional neural networks for bird detection in audio signals. In Proc. EUSIPCO (pp. 1764\u20131768)","DOI":"10.23919\/EUSIPCO.2017.8081512"},{"key":"9957_CR10","unstructured":"Himawan, I., Towsey, M., & Roe, P. (2018). 3D convolutional recurrent neural networks for bird sound detection. In Proc. DCASE workshop pp.108\u2013112."},{"key":"9957_CR11","unstructured":"IEEE AASP challenge on detection and classification of acoustic scenes and events. DCASE2018 Challenge. http:\/\/dcase.community\/challenge2018\/task-bird-audio-detection"},{"key":"9957_CR12","unstructured":"Jamali, S., Ahmadpanah, J., & Alipoor, G. (2018). Bird audio detection using supervised weighted NMF. In DCASE challenge"},{"key":"9957_CR13","unstructured":"Kong, Q., Iqbal, T., Xu, Y., et al. (2018). DCASE 2018 challenge SURREY cross-task convolutional neural network baseline. In Proc. DCASE Workshop (pp. 217\u2013221)."},{"key":"9957_CR14","first-page":"335","volume-title":"Audio event recognition in the smart home","author":"S Krstulovic","year":"2018","unstructured":"Krstulovic, S. (2018). Audio event recognition in the smart home. Computational analysis of sound scenes and events (pp. 335\u2013371). Springer."},{"key":"9957_CR15","unstructured":"Lasseck, M. (2018). Acoustic bird detection with deep convolutional neural networks. In Proc. DCASE Workshop (pp. 143\u2013147)"},{"key":"9957_CR16","unstructured":"Liaqat, S., Bozorg, N., Jose, N., Conrey, P., Tamasi, A., & Johnson, M. T. (2018). Domain tuning methods for bird audio detection. In Proc. DCASE Workshop (pp. 163\u2013167)"},{"issue":"1","key":"9957_CR17","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/LSP.2018.2878620","volume":"26","author":"V Lostanlen","year":"2019","unstructured":"Lostanlen, V., et al. (2019). Per-channel energy normalization: Why and how. IEEE Signal Processing Letters, 26(1), 39\u201343.","journal-title":"IEEE Signal Processing Letters"},{"key":"9957_CR18","doi-asserted-by":"crossref","unstructured":"Lostanlen, V., Salamon, J., Farnsworth, A., Kelling, S., & Bello, J. P. (2018). Birdvox-full-night: A dataset and benchmark for avian flight call detection. In Proc. ICASSP (pp. 266\u2013270).","DOI":"10.1109\/ICASSP.2018.8461410"},{"key":"9957_CR19","unstructured":"Mukherjee, R., Banerjee, D., Dey, K., & Ganguly, N. (2018). Convolutional recurrent neural network based bird audio detection. In DCASE challenge."},{"key":"9957_CR20","unstructured":"M\u00fcller, D. (2014). Disch. Extending harmonic-percussive separation of audio. In Pro. ISMIR (pp. 611\u2013616)."},{"key":"9957_CR22","unstructured":"Ono, N., Miyamoto, K., Kameoka, H., & Sagayama, S. (2008a). A real-time equalizer of harmonic and percussive components in music signals. In Proc. ISMIR (pp. 139\u2013144)."},{"key":"9957_CR21","unstructured":"Ono, N., Miyamoto, K., Roux, J. L., Kameoka, H., & Sagayama, S. (2008b). Separation of a monaural audio signal into harmonic\/percussive components by complementary diffusion on spectrogram. In Proc. EUSIPCO (pp. 240\u2013244)."},{"key":"9957_CR23","doi-asserted-by":"crossref","unstructured":"Park, D. S., Chan, W., Zhang, Y., et al. (2019). SpecAugment: A simple data augmentation method for automatic speech recognition. In Proc. Interspeech (pp. 2613\u20132617).","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"9957_CR24","doi-asserted-by":"crossref","unstructured":"Porter, J., & Boll, S. (1984). Optimal estimators for spectral restoration of noisy speech. In Proc. ICASSP (pp. 53\u201356).","DOI":"10.1109\/ICASSP.1984.1172545"},{"key":"9957_CR25","unstructured":"Schluter, J., & Lehner, B. (2018). Zero-mean convolutions for level-invariant singing voice detection. In Proc. ISMIR (pp. 1\u20136)."},{"key":"9957_CR26","unstructured":"Shen, J., Qu, Y., Zhang, W., & Yu, Y. (2018). Wasserstein distance guided representation learning for domain adaptation, AAAI (pp. 4058\u20134065)."},{"key":"9957_CR27","unstructured":"Song, J., & Li, S. (2018). Bird audio detection using convolutional neural networks and binary neural networks. In DCASE challenge."},{"key":"9957_CR28","doi-asserted-by":"crossref","unstructured":"Sun, B., Feng, J., & Saenko, K. (2016). Return of frustratingly easy domain adaptation, in Proc. AAAI (pp. 2058\u20132065).","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"9957_CR29","unstructured":"Vesperini, F., Gabrielli, L., Principi, E., & Squartini, S. (2018). A capsule neural networks based approach for bird audio detection. In DCASE Challenge."},{"key":"9957_CR30","doi-asserted-by":"crossref","unstructured":"Vincent, L., Salamon, J., Farnsworth, A., et al. (2019). Robust sound event detection in bioacoustic sensor networks. PLoS ONE, 14(10).","DOI":"10.1371\/journal.pone.0214168"},{"key":"9957_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., Getreuer, P., Hughes, T., Lyon, R. F., & Saurous, R. A. (2017). Trainable frontend for robust and far-field keyword spotting. In Proc. ICASSP (pp. 5670\u20135674).","DOI":"10.1109\/ICASSP.2017.7953242"},{"key":"9957_CR32","doi-asserted-by":"publisher","first-page":"175353","DOI":"10.1109\/ACCESS.2019.2957572","volume":"7","author":"J Xie","year":"2019","unstructured":"Xie, J., Hu, K., Zhu, M., Yu, J., & Zhu, Q. (2019). Investigation of different CNN-based models for improved bird sound classification. IEEE Access, 7, 175353\u2013175361.","journal-title":"IEEE Access"},{"key":"9957_CR33","unstructured":"Yu, C. C, Hao, Y., Yang, W. B., & Fu, B. (2018). Author guidelines for DCASE2018 challenge technical report. In DCASE challenge"},{"key":"9957_CR34","doi-asserted-by":"crossref","unstructured":"Zinemanas, P., Cancela, P., & Rocamora, M. (2019). End-to-end convolutional neural networks for sound event detection in urban environments. In Proc. FRUCT (pp. 533\u2013539).","DOI":"10.23919\/FRUCT.2019.8711906"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09957-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-022-09957-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09957-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T19:08:47Z","timestamp":1674414527000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-022-09957-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,12]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["9957"],"URL":"https:\/\/doi.org\/10.1007\/s10772-022-09957-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,12]]},"assertion":[{"value":"29 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}