{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:24:18Z","timestamp":1761110658775,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T00:00:00Z","timestamp":1667347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T00:00:00Z","timestamp":1667347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021ZY87"],"award-info":[{"award-number":["2021ZY87"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01447-9","type":"journal-article","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T05:02:27Z","timestamp":1667365347000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-domain Attention Fusion Network For Language Recognition"],"prefix":"10.1007","volume":"4","author":[{"given":"Minghang","family":"Ju","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7174-6588","authenticated-orcid":false,"given":"Yanyan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengfeng","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaile","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,2]]},"reference":[{"issue":"5","key":"1447_CR1","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1109\/JPROC.2012.2237151","volume":"101","author":"H Li","year":"2013","unstructured":"Li H, Ma B, Lee KA. Spoken language recognition: from fundamentals to practice. Proc IEEE. 2013;101(5):1136\u201359.","journal-title":"Proc IEEE"},{"issue":"8","key":"1447_CR2","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1109\/5.880085","volume":"88","author":"A Waibel","year":"2000","unstructured":"Waibel A, Geutner P, Tomokiyo LM, Schultz T, Woszczyna M. Multilinguality in speech and spoken language systems. Proc IEEE. 2000;88(8):1297\u2013313.","journal-title":"Proc IEEE"},{"key":"1447_CR3","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.neunet.2021.03.014","volume":"139","author":"X Miao","year":"2021","unstructured":"Miao X, McLoughlin I, Wang W, Zhang P. D-mona: a dilated mixed-order non-local attention network for speaker and language recognition. Neural Netw. 2021;139:201\u201311.","journal-title":"Neural Netw"},{"key":"1447_CR4","doi-asserted-by":"crossref","unstructured":"Dehak N, Torres-Carrasquillo PA, Reynolds D, Dehak R. Language recognition via i-vectors and dimensionality reduction. In: Twelfth annual conference of the international speech communication association. Citeseer (2011)","DOI":"10.21437\/Interspeech.2011-328"},{"issue":"4","key":"1447_CR5","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak N, Kenny PJ, Dehak R, Dumouchel P, Ouellet P. Front-end factor analysis for speaker verification. IEEE Trans Audio Speech Lang Process. 2010;19(4):788\u201398.","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1447_CR6","doi-asserted-by":"crossref","unstructured":"Huang J-T, Li J, Yu D, Deng L, Gong Y. Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers. In: 2013 IEEE International conference on acoustics, speech and signal processing, pp. 7304\u20137308 (2013). IEEE","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"1447_CR7","doi-asserted-by":"crossref","unstructured":"Heigold G, Moreno I, Bengio S, Shazeer N. End-to-end text-dependent speaker verification. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5115\u20135119 (2016). IEEE","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"1447_CR8","doi-asserted-by":"crossref","unstructured":"Cai W, Cai Z, Liu W, Wang X, Li M. Insights in-to-end learning scheme for language identification. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5209\u20135213 (2018). IEEE","DOI":"10.1109\/ICASSP.2018.8462026"},{"key":"1447_CR9","doi-asserted-by":"crossref","unstructured":"Wu H, Cai W, Li M, Gao J, Zhang S, Lyu Z, Huang S: DKU-tencent submission to oriental language recognition AP18-OLR challenge. In: 2019 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC), pp. 1646\u20131651 (2019). IEEE","DOI":"10.1109\/APSIPAASC47483.2019.9023189"},{"key":"1447_CR10","doi-asserted-by":"crossref","unstructured":"Miao X, McLoughlin I, Yan Y. A new time-frequency attention mechanism for TDNN and CNN-LSTM-TDNN, with application to language identification. In: Interspeech, pp. 4080\u20134084 (2019)","DOI":"10.21437\/Interspeech.2019-1256"},{"key":"1447_CR11","doi-asserted-by":"crossref","unstructured":"Zhou J, Jiang T, Li Z, Li L, Hong Q. Deep speaker embedding extraction with channel-wise feature responses and additive supervision softmax loss function. In: Interspeech, pp. 2883\u20132887 (2019)","DOI":"10.21437\/Interspeech.2019-1704"},{"key":"1447_CR12","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1447_CR13","doi-asserted-by":"crossref","unstructured":"Yadav S, Rai A. Frequency and temporal convolutional attention for text-independent speaker recognition. In: ICASSP 2020\u20132020 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 6794\u20136798 (2020). IEEE","DOI":"10.1109\/ICASSP40776.2020.9054440"},{"key":"1447_CR14","doi-asserted-by":"crossref","unstructured":"Miao X, McLoughlin IV, Yan Y. A new time-frequency attention mechanism for TDNN and CNN-LSTM-TDNN, with application to language identification. In: Interspeech, pp. 4080\u20134084 (2019)","DOI":"10.21437\/Interspeech.2019-1256"},{"key":"1447_CR15","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS. CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1447_CR16","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H. Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1447_CR17","doi-asserted-by":"crossref","unstructured":"Qin Z, Zhang P, Wu F, Li X. Fcanet: frequency channel attention networks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 783\u2013792 (2021)","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"1447_CR18","doi-asserted-by":"crossref","unstructured":"Shi Y, Huang Q, Hain T. Robust speaker recognition using speech enhancement and attention model. arXiv preprint arXiv:2001.05031 (2020)","DOI":"10.21437\/Odyssey.2020-65"},{"key":"1447_CR19","doi-asserted-by":"crossref","unstructured":"Gao Z, Xie J, Wang Q, Li P. Global second-order pooling convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3024\u20133033 (2019)","DOI":"10.1109\/CVPR.2019.00314"},{"issue":"6","key":"1447_CR20","doi-asserted-by":"publisher","first-page":"5183","DOI":"10.1109\/TGRS.2020.3009918","volume":"59","author":"D Zhang","year":"2020","unstructured":"Zhang D, Shao J, Li X, Shen HT. Remote sensing image super-resolution via mixed high-order attention network. IEEE Trans Geosci Remote Sens. 2020;59(6):5183\u201396.","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1447_CR21","doi-asserted-by":"crossref","unstructured":"Cai W, Cai Z, Zhang X, Wang X, Li M. A novel learnable dictionary encoding layer for end-to-end language identification. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5189\u20135193 (2018). IEEE","DOI":"10.1109\/ICASSP.2018.8462025"},{"key":"1447_CR22","doi-asserted-by":"crossref","unstructured":"Padi B, Mohan A, Ganapathy S: Attention based hybrid i-vector blstm model for language recognition. In: INTERSPEECH, pp. 1263\u20131267 (2019)","DOI":"10.21437\/Interspeech.2019-2371"},{"key":"1447_CR23","doi-asserted-by":"crossref","unstructured":"Cai W, Cai D, Huang S, Li M : Utterance-level end-to-end language identification using attention-based CNN-BLSTM. In: ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5991\u20135995 (2019). IEEE","DOI":"10.1109\/ICASSP.2019.8682386"},{"key":"1447_CR24","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/TASLP.2020.2983580","volume":"28","author":"B Padi","year":"2020","unstructured":"Padi B, Mohan A, Ganapathy S. Towards relevance and sequence modeling in language recognition. IEEE\/ACM Trans Audio Speech Lang Process. 2020;28:1223\u201332.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"1447_CR25","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Xue N, Zafeiriou S. Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"1447_CR26","doi-asserted-by":"crossref","unstructured":"Cai W, Chen J, Li M: Exploring the encoding layer and loss function in end-to-end speaker and language recognition system. arXiv preprint arXiv:1804.05160 (2018)","DOI":"10.21437\/Odyssey.2018-11"},{"key":"1447_CR27","doi-asserted-by":"crossref","unstructured":"Tang Z, Wang D, Chen Y, Chen Q. AP17-OLR challenge: data, plan, and baseline. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 749\u2013753 (2017). IEEE","DOI":"10.1109\/APSIPA.2017.8282134"},{"key":"1447_CR28","doi-asserted-by":"crossref","unstructured":"Wang D, Li L, Tang D, Chen Q. AP16-OL7: a multilingual database for oriental languages and a language recognition baseline. In: 2016 Asia-Pacific signal and information processing association annual summit and conference (APSIPA), pp. 1\u20135 (2016). IEEE","DOI":"10.1109\/APSIPA.2016.7820796"},{"key":"1447_CR29","unstructured":"Li Z, Zhao M, Hong Q, Li L, Tang Z, Wang, D, Song L, Yang C. AP20-OLR challenge: three tasks and their baselines. In: 2020 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC), pp. 550\u2013555 (2020). IEEE"},{"key":"1447_CR30","unstructured":"Ma Z, Yu H. Language identification with deep bottleneck features. arXiv preprint arXiv:1809.08909 (2018)"},{"key":"1447_CR31","doi-asserted-by":"crossref","unstructured":"Ko T, Peddinti V, Povey D, Seltzer ML, Khudanpur S. A study on data augmentation of reverberant speech for robust speech recognition. In: 2017 IEEE International conference on acoustics, speech and signal processing (ICASSP), pp. 5220\u20135224 (2017). IEEE","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"1447_CR32","unstructured":"Snyder D, Chen G, Povey D. MUSAN: a music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)"},{"key":"1447_CR33","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TASLP.2020.2980991","volume":"28","author":"W Cai","year":"2020","unstructured":"Cai W, Chen J, Zhang J, Li M. On-the-fly data loader and utterance-level aggregation for speaker and language recognition. IEEE\/ACM Trans Audio Speech Lang Process. 2020;28:1038\u201351.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"1447_CR34","doi-asserted-by":"crossref","unstructured":"Snyder D, Garcia-Romero D, Sell G, Povey D, Khudanpur S: X-vectors: Robust DNN embeddings for speaker recognition. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5329\u20135333 (2018) IEEE","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"1447_CR35","doi-asserted-by":"crossref","unstructured":"Qi Z, Ma Y, Gu M. A study on low-resource language identification. In: 2019 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC), pp. 1897\u20131902 (2019). IEEE","DOI":"10.1109\/APSIPAASC47483.2019.9023075"},{"key":"1447_CR36","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al. Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)"},{"key":"1447_CR37","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/TASLP.2020.2983580","volume":"28","author":"B Padi","year":"2020","unstructured":"Padi B, Mohan A, Ganapathy S. Towards relevance and sequence modeling in language recognition. IEEE\/ACM Trans Audio Speech Lang Process. 2020;28:1223\u201332.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"1447_CR38","doi-asserted-by":"crossref","unstructured":"Tang Z, Wang D, Chen Q. AP18-OLR challenge: three tasks and their baselines. CoRR abs\/1806.00616 (2018) 1806.00616","DOI":"10.23919\/APSIPA.2018.8659714"},{"key":"1447_CR39","doi-asserted-by":"crossref","unstructured":"Fernando S, Sethu V, Ambikairajah E. Factorized hidden variability learning for adaptation of short duration language identification models. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5204\u20135208 (2018). IEEE","DOI":"10.1109\/ICASSP.2018.8462094"},{"key":"1447_CR40","doi-asserted-by":"crossref","unstructured":"Yu J, Guo M, Xie Y, Zhang J. Articulatory features based tdnn model for spoken language recognition. In: 2019 International conference on Asian language processing (IALP), pp. 308\u2013312 (2019). IEEE","DOI":"10.1109\/IALP48816.2019.9037566"},{"key":"1447_CR41","doi-asserted-by":"crossref","unstructured":"Vuddagiri RK, Mandava T, Vydana HK, Vuppala AK. Multi-head self-attention networks for language identification. In: 2019 Twelfth international conference on contemporary computing (IC3), pp. 1\u20135 (2019). IEEE","DOI":"10.1109\/IC3.2019.8844925"},{"key":"1447_CR42","doi-asserted-by":"crossref","unstructured":"Fan Z, Li M, Zhou S, Xu B. Exploring wav2vec 2.0 on speaker verification and language identification. arXiv preprint arXiv:2012.06185 (2020)","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"1447_CR43","doi-asserted-by":"crossref","unstructured":"Li J, Wang B, Zhi Y, Li Z, Li L, Hong Q, Wang D. Oriental language recognition (olr) 2020: Summary and analysis. arXiv preprint arXiv:2107.05365 (2021)","DOI":"10.21437\/Interspeech.2021-2171"},{"key":"1447_CR44","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.neunet.2021.03.026","volume":"141","author":"L Li","year":"2021","unstructured":"Li L, Li Z, Liu Y, Hong Q. Deep joint learning for language recognition. Neural Netw. 2021;141:72\u201386.","journal-title":"Neural Netw"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01447-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01447-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01447-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T22:23:15Z","timestamp":1673130195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01447-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,2]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["1447"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01447-9","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2022,11,2]]},"assertion":[{"value":"23 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"39"}}