{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:57:56Z","timestamp":1783141076518,"version":"3.54.6"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key Projects of the National Natural Science Foundation of China","award":["U1836220"],"award-info":[{"award-number":["U1836220"]}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["62176106"],"award-info":[{"award-number":["62176106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006098"],"award-info":[{"award-number":["62006098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province key research and development plan","award":["BE2020036"],"award-info":[{"award-number":["BE2020036"]}]},{"name":"Fellowship of China Postdoctoral Science Foundation","award":["2020M681515"],"award-info":[{"award-number":["2020M681515"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s10044-023-01172-w","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:02:01Z","timestamp":1687280521000},"page":"1089-1099","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-level distance embedding learning for robust acoustic scene classification with unseen devices"],"prefix":"10.1007","volume":"26","author":[{"given":"Gang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongchen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0616-4431","authenticated-orcid":false,"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,20]]},"reference":[{"key":"1172_CR1","unstructured":"Yuanbo H, Bo K, Hauwermeiren V W, Botteldooren D (2022) Relation-guided acoustic scene classification aided with event embeddings. arXiv preprint arXiv:2205.00499"},{"issue":"3","key":"1172_CR2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MSP.2014.2326181","volume":"32","author":"D Barchiesi","year":"2015","unstructured":"Barchiesi D, Giannoulis D, Stowell D, Plumbley M (2015) Acoustic scene classification: classifying environments from the sounds they produce. IEEE Signal Process Mag 32(3):16\u201334","journal-title":"IEEE Signal Process Mag"},{"key":"1172_CR3","unstructured":"Byeonggeun K, Seunghan Y, Jangho K, Hyunsin P, Juntae L, Simyung C (2022) Domain generalization with relaxed instance frequency-wise normalization for multi-device acoustic scene classification. arXiv preprint arXiv:2206.12513"},{"issue":"10","key":"1172_CR4","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","volume":"17","author":"D Stowell","year":"2015","unstructured":"Stowell D, Giannoulis D, Benetos E, Lagrange M, Plumbley M (2015) Detection and classification of acoustic scenes and events. IEEE Trans Multimedia 17(10):1733\u20131746","journal-title":"IEEE Trans Multimedia"},{"issue":"3","key":"1172_CR5","first-page":"465","volume":"43","author":"K Qian","year":"2018","unstructured":"Qian K, Janott C, Zhang Z, Deng J, Baird A, Heiser C, Hohenhorst W, Herzog M, Hemmert W, Schuller B (2018) Teaching machines on snoring: a benchmark on computer audition for snore sound excitation localisation. Arch Acoustics 43(3):465\u2013475","journal-title":"Arch Acoustics"},{"issue":"1","key":"1172_CR6","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1109\/SURV.2013.042313.00197","volume":"16","author":"C Perera","year":"2014","unstructured":"Perera C, Zaslavsky A, Christen P, Georgakopoulos D (2014) Context aware computing for the internet of things: A survey. IEEE Commun Surv Tutor 16(1):414\u2013454","journal-title":"IEEE Commun Surv Tutor"},{"key":"1172_CR7","unstructured":"Harma A, Jakka J, Tikander M, Karjalainen M, Lokki T, Nironen H (2003) Techniques and applications for wearable augmented reality audio. In: Audio engineering society convention 114. audio engineering"},{"key":"1172_CR8","doi-asserted-by":"crossref","unstructured":"Martinson AE (2007) Robotic discovery of the auditory scene. In: robotics and automation, 2007 IEEE international conference on","DOI":"10.1109\/ROBOT.2007.363825"},{"key":"1172_CR9","unstructured":"Qian K, Zhao R, Pandit V, Yang Z, Schuller B (2017) Wavelets revisited for the classification of acoustic scenes. In: workshop on detection and classification of acoustic scenes and events"},{"key":"1172_CR10","unstructured":"Amiriparian S, Freitag M, Cummins N, Schuller B (2017) Sequence to sequence autoencoders for unsupervised representation learning from audio"},{"key":"1172_CR11","doi-asserted-by":"crossref","unstructured":"Hershey S, Chaudhuri S, Ellis D, Gemmeke JF, Jansen A, Moore RC, Plakal M, Platt D, Saurous RA, Seybold B (2017) Cnn architectures for large-scale audio classification. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 131\u2013135. IEEE","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"1172_CR12","doi-asserted-by":"crossref","unstructured":"Ren Z, Kong Q, Han J, Plumbley M, Schuller BW (2019) Attention-based atrous convolutional neural networks: Visualisation and understanding perspectives of acoustic scenes. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), Brighton, UK, pp 56\u201360","DOI":"10.1109\/ICASSP.2019.8683434"},{"key":"1172_CR13","unstructured":"Wang H, Zou Y, Chong D (2020) Acoustic scene classification with spectrogram processing strategies"},{"issue":"3","key":"1172_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24(3):1\u20131","journal-title":"IEEE Signal Process Lett"},{"issue":"6","key":"1172_CR15","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.3390\/app10062020","volume":"10","author":"J Abeer","year":"2020","unstructured":"Abeer J (2020) A review of deep learning based methods for acoustic scene classification. Appl Sci 10(6):2020","journal-title":"Appl Sci"},{"key":"1172_CR16","unstructured":"Suh S, Park S, Jeong Y, Lee T (June 2020) Designing acoustic scene classification models with CNN variants. Technical report, DCASE2020 challenge"},{"key":"1172_CR17","doi-asserted-by":"crossref","unstructured":"Hu H, Yang C, Xia X, Bai X, Lee CH (2020) Device-robust acoustic scene classification based on two-stage categorization and data augmentation","DOI":"10.1109\/ICASSP39728.2021.9414835"},{"key":"1172_CR18","doi-asserted-by":"crossref","unstructured":"Hu H, Yang C, Xia X, Bai X, Lee CH (2021) A two-stage approach to device-robust acoustic scene classification. In: ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 845\u2013849. IEEE","DOI":"10.1109\/ICASSP39728.2021.9414835"},{"key":"1172_CR19","doi-asserted-by":"crossref","unstructured":"Gao W, Mcdonnell M (June 2020) Acoustic scene classification using deep residual networks with focal loss and mild domain adaptation. Technical report, DCASE2020 Challenge","DOI":"10.1109\/ICASSP40776.2020.9053274"},{"key":"1172_CR20","unstructured":"Jie L (June 2020) Acoustic scene classification with residual networks and attention mechanism. Technical report, DCASE2020 Challenge"},{"key":"1172_CR21","doi-asserted-by":"crossref","unstructured":"Mcdonnell M, Gao W (2020) Acoustic scene classification using deep residual networks with late fusion of separated high and low frequency paths. In: ICASSP 2020 - 2020 IEEE international conference on acoustics, speech and signal processing (ICASSP)","DOI":"10.1109\/ICASSP40776.2020.9053274"},{"key":"1172_CR22","unstructured":"Jie H, Li S, Gang S, Albanie S (2019) Squeeze-and-excitation networks. IEEE transactions on pattern analysis and machine intelligence"},{"key":"1172_CR23","volume-title":"Cbam: convolutional block attention module","author":"S Woo","year":"2018","unstructured":"Woo S, Park J, Lee JY, Kweon IS (2018) Cbam: convolutional block attention module. Springer, Cham"},{"key":"1172_CR24","unstructured":"Bochkovskiy A, Wang CY, Liao H (2020) Yolov4: Optimal speed and accuracy of object detection"},{"key":"1172_CR25","unstructured":"Hadsell R, Chopra S, Lecun Y (2006) Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201906)"},{"key":"1172_CR26","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. IEEE","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"1172_CR27","doi-asserted-by":"crossref","unstructured":"Kim Y, Park W (2021) Multi-level distance regularization for deep metric learning. CoRR arXiv:2102.04223","DOI":"10.1609\/aaai.v35i3.16277"},{"key":"1172_CR28","doi-asserted-by":"publisher","unstructured":"Heittola T, Mesaros A, Virtanen, T.: TAU Urban Acoustic Scenes, (2020) Mobile. Development Dataset. https:\/\/doi.org\/10.5281\/zenodo.3819968","DOI":"10.5281\/zenodo.3819968"},{"key":"1172_CR29","doi-asserted-by":"crossref","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) mixup: Beyond empirical risk minimization","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"1172_CR30","doi-asserted-by":"crossref","unstructured":"Koutini K, Eghbal-Zadeh H, Dorfer M, Widmer G (2019) The receptive field as a regularizer in deep convolutional neural networks for acoustic scene classification","DOI":"10.23919\/EUSIPCO.2019.8902732"},{"key":"1172_CR31","doi-asserted-by":"crossref","unstructured":"Cramer J, Wu HH, Salamon J, Bello JP (2019) Look, listen and learn more: Design choices for deep audio embeddings. In: IEEE Int. $$\\tilde{}$$Conf.$$\\tilde{}$$on acoustics, speech and signal processing (ICASSP), Brighton, UK, pp 3852\u20133856. https:\/\/ieeexplore.ieee.org\/document\/8682475","DOI":"10.1109\/ICASSP.2019.8682475"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-023-01172-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-023-01172-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-023-01172-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,22]],"date-time":"2023-07-22T14:10:07Z","timestamp":1690035007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-023-01172-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,20]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["1172"],"URL":"https:\/\/doi.org\/10.1007\/s10044-023-01172-w","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,20]]},"assertion":[{"value":"14 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}