{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:54:44Z","timestamp":1767142484785,"version":"build-2238731810"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T00:00:00Z","timestamp":1757203200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T00:00:00Z","timestamp":1757203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62101163"],"award-info":[{"award-number":["No.62101163"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["No.YQ2024F018"],"award-info":[{"award-number":["No.YQ2024F018"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Foundation for Universities of Heilongjiang Province","award":["No.2021-KYYWF-0762"],"award-info":[{"award-number":["No.2021-KYYWF-0762"]}]},{"name":"Key Research and Development Project of Heilongjiang Province","award":["No.JD2023SJ20"],"award-info":[{"award-number":["No.JD2023SJ20"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07808-4","type":"journal-article","created":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T15:45:21Z","timestamp":1757259921000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Language identification based on multi-scale feature recursive fusion and adaptive loss"],"prefix":"10.1007","volume":"81","author":[{"given":"Weiwei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deyun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"key":"7808_CR1","doi-asserted-by":"publisher","first-page":"103167","DOI":"10.1016\/j.specom.2024.103167","volume":"167","author":"D O\u2019Shaughnessy","year":"2025","unstructured":"O\u2019Shaughnessy D (2025) Spoken language identification: an overview of past and present research trends. Speech Commun 167:103167","journal-title":"Speech Commun"},{"issue":"1","key":"7808_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s42979-022-01447-9","volume":"4","author":"M Ju","year":"2022","unstructured":"Ju M, Xu Y, Ke D et al (2022) Multi-domain attention fusion network for language recognition. SN Comput Sci 4(1):39","journal-title":"SN Comput Sci"},{"key":"7808_CR3","doi-asserted-by":"publisher","first-page":"101869","DOI":"10.1016\/j.inffus.2023.101869","volume":"99","author":"A Mehrish","year":"2023","unstructured":"Mehrish A, Majumder N, Bharadwaj R et al (2023) A review of deep learning techniques for speech processing. Inform Fusion 99:101869","journal-title":"Inform Fusion"},{"issue":"12","key":"7808_CR4","doi-asserted-by":"publisher","first-page":"34499","DOI":"10.1007\/s11042-023-17094-y","volume":"83","author":"AA Alemu","year":"2024","unstructured":"Alemu AA, Melese MD, Salau AO (2024) Ethio-semitic language identification using convolutional neural networks with data augmentation. Multimed Tools Appl 83(12):34499\u201334514","journal-title":"Multimed Tools Appl"},{"key":"7808_CR5","unstructured":"Dey S, Mondal H, Kurmi SK (2025) Teacher-free knowledge distillation for improving short-utterance spoken language identification. In: Proceedings of Interspeech 2025, pp 1483\u20131487"},{"key":"7808_CR6","doi-asserted-by":"crossref","unstructured":"Conneau A, Ma M, Khanuja S et\u00a0al (2023) Fleurs: few-shot learning evaluation of universal representations of speech. In: 2022 IEEE Spoken Language Technology Workshop (SLT) (IEEE), pp 798\u2013805","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"7808_CR7","unstructured":"Radford A, Kim JW, Xu T et\u00a0al (2023) Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning (PMLR), pp 28492\u201328518"},{"key":"7808_CR8","doi-asserted-by":"publisher","first-page":"2071","DOI":"10.1007\/s11277-019-06373-3","volume":"107","author":"D Deshwal","year":"2019","unstructured":"Deshwal D, Sangwan P, Kumar D (2019) Feature extraction methods in language identification: a survey. Wireless Pers Commun 107:2071\u20132103","journal-title":"Wireless Pers Commun"},{"key":"7808_CR9","doi-asserted-by":"publisher","first-page":"46335","DOI":"10.1109\/ACCESS.2020.2974101","volume":"8","author":"D Wang","year":"2020","unstructured":"Wang D, Su J, Yu H (2020) Feature extraction and analysis of natural language processing for deep learning english language. IEEE Access 8:46335\u201346345","journal-title":"IEEE Access"},{"key":"7808_CR10","doi-asserted-by":"crossref","unstructured":"Wan L, Sridhar P, Yu Y et\u00a0al (2019) Tuplemax loss for language identification. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE), pp 5976\u20135980","DOI":"10.1109\/ICASSP.2019.8683313"},{"issue":"24","key":"7808_CR11","doi-asserted-by":"publisher","first-page":"28951","DOI":"10.1007\/s11042-024-20283-y","volume":"84","author":"H Tomar","year":"2025","unstructured":"Tomar H, Deshwal D, Trivedi N (2025) Convolutional neural network based language identification system: a spectrogram based approach. Multimed Tools Appl 84(24):28951\u201328976","journal-title":"Multimed Tools Appl"},{"key":"7808_CR12","unstructured":"Arora S, Chang KW, Chien CM et\u00a0al (2025) On the landscape of spoken language models: a comprehensive survey. arXiv preprint arXiv:2504.08528"},{"issue":"2","key":"7808_CR13","first-page":"116","volume":"46","author":"YK Yu","year":"2023","unstructured":"Yu YK, Hua M, Yu YB et al (2023) Language identification method based on fusion feature mgcc. J Beijing Univ Posts Telecommun 46(2):116","journal-title":"J Beijing Univ Posts Telecommun"},{"key":"7808_CR14","doi-asserted-by":"crossref","unstructured":"i Ambili AR, Roy RC (2024) Local and global context feature fusion for effective spoken language ientification in Indian Linguistics. In: 2024 International Conference on Smart Electronics and Communication Systems (ISENSE) (IEEE), pp 1\u20136","DOI":"10.1109\/ISENSE63713.2024.10872051"},{"key":"7808_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-024-19253-1","volume":"84","author":"MS Sidhu","year":"2024","unstructured":"Sidhu MS, Latib NAA, Sidhu KK (2024) MFCC in audio signal processing for voice disorder: a review. Multimed Tools Appl 84:1\u201321","journal-title":"Multimed Tools Appl"},{"key":"7808_CR16","doi-asserted-by":"crossref","unstructured":"Misra S, Das TK, Saha P et\u00a0al (2015) Comparison of MFCC and LPCC for a fixed phrase speaker verification system, time complexity and failure analysis. In: 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015] (IEEE), pp 1\u20134","DOI":"10.1109\/ICCPCT.2015.7159307"},{"issue":"2","key":"7808_CR17","first-page":"148","volume":"29","author":"A Rasheed","year":"2024","unstructured":"Rasheed A (2024) Analyzing the mfcc and gfcc to identify reverberation effects on the sound. Al-Rafidain Eng J 29(2):148\u2013156","journal-title":"Al-Rafidain Eng J"},{"key":"7808_CR18","doi-asserted-by":"crossref","unstructured":"He Y, Xu L (2024) Channel attention concatenation multi-taper Fbank features for deep speaker verification. In: Fourth International Conference on Advanced Algorithms and Neural Networks (AANN 2024), vol 13416 (SPIE), pp 628\u2013634","DOI":"10.1117\/12.3049499"},{"issue":"7","key":"7808_CR19","doi-asserted-by":"publisher","first-page":"4235","DOI":"10.3390\/app13074235","volume":"13","author":"Z Aysa","year":"2023","unstructured":"Aysa Z, Ablimit M, Hamdulla A (2023) Multi-scale feature learning for language identification of overlapped speech. Appl Sci 13(7):4235","journal-title":"Appl Sci"},{"key":"7808_CR20","doi-asserted-by":"publisher","first-page":"109752","DOI":"10.1016\/j.apacoust.2023.109752","volume":"216","author":"L Yu","year":"2024","unstructured":"Yu L, Xu F, Qu Y et al (2024) Speech emotion recognition based on multi-dimensional feature extraction and multi-scale feature fusion. Appl Acoust 216:109752","journal-title":"Appl Acoust"},{"key":"7808_CR21","doi-asserted-by":"crossref","unstructured":"Gupta S, Motepalli KSS, Kumar R et\u00a0al (2023) Enhancing language identification in indian context through exploiting learned features with wav2vec2. 0. In: International Conference on Speech and Computer (Springer Nature Switzerland, Cham), pp 503\u2013512","DOI":"10.1007\/978-3-031-48312-7_40"},{"key":"7808_CR22","unstructured":"Kounadis-Bastian D, Schr\u00fcfer O, Derington A et\u00a0al (2024) Wav2small: Distilling wav2vec2 to 72k parameters for low-resource speech emotion recognition. arXiv preprint arXiv:2408.13920"},{"key":"7808_CR23","unstructured":"van\u00a0der Merwe R (2020) Triplet entropy loss: improving the generalisation of short speech language identification systems. arXiv preprint arXiv:2012.03775"},{"key":"7808_CR24","doi-asserted-by":"crossref","unstructured":"Duroselle R, Jouvet D, Illina I (2020) Metric learning loss functions to reduce domain mismatch in the x-vector space for language recognition, in INTERSPEECH 2020","DOI":"10.21437\/Interspeech.2020-1708"},{"key":"7808_CR25","doi-asserted-by":"crossref","unstructured":"Muralikrishna H, Kapoor S, Dinesh DA et\u00a0al (2021) Spoken language identification in unseen target domain using within-sample similarity loss. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE), pp 7223\u20137227","DOI":"10.1109\/ICASSP39728.2021.9414090"},{"issue":"2","key":"7808_CR26","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s40745-020-00253-5","volume":"9","author":"Q Wang","year":"2022","unstructured":"Wang Q, Ma Y, Zhao K et al (2022) A comprehensive survey of loss functions in machine learning. Ann Data Sci 9(2):187\u2013212","journal-title":"Ann Data Sci"},{"key":"7808_CR27","unstructured":"Mao A, Mohri M, Zhong Y (2023) Cross-entropy loss functions: theoretical analysis and applications. In: International conference on Machine learning (PMLR), pp 23803\u201323828"},{"issue":"6","key":"7808_CR28","doi-asserted-by":"publisher","first-page":"491","DOI":"10.3390\/e26060491","volume":"26","author":"R Connor","year":"2024","unstructured":"Connor R, Dearle A, Claydon B et al (2024) Correlations of cross-entropy loss in machine learning. Entropy 26(6):491","journal-title":"Entropy"},{"key":"7808_CR29","first-page":"1","volume":"29","author":"K Sohn","year":"2016","unstructured":"Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. Adv Neural Inform Process Syst 29:1\u20139","journal-title":"Adv Neural Inform Process Syst"},{"issue":"12","key":"7808_CR30","doi-asserted-by":"publisher","first-page":"3180","DOI":"10.1109\/TMM.2020.2972125","volume":"22","author":"C Zhao","year":"2020","unstructured":"Zhao C, Lv X, Zhang Z et al (2020) Deep fusion feature representation learning with hard mining center-triplet loss for person re-identification. IEEE Trans Multimed 22(12):3180\u20133195","journal-title":"IEEE Trans Multimed"},{"key":"7808_CR31","doi-asserted-by":"crossref","unstructured":"Qian Q, Shang L, Sun B et\u00a0al (2019) Softtriple loss: Deep metric learning without triplet sampling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6450\u20136458","DOI":"10.1109\/ICCV.2019.00655"},{"key":"7808_CR32","doi-asserted-by":"crossref","unstructured":"Cai W, Chen J, Li M (2018) Exploring the encoding layer and loss function in endto-end speaker and language recognition system. In: The Speaker and Language Recognition Workshop (Odyssey) (ISCA), pp 74\u201381","DOI":"10.21437\/Odyssey.2018-11"},{"issue":"7","key":"7808_CR33","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang F, Cheng J, Liu W, Liu H (2018) Additive margin softmax for face verification. IEEE Signal Process Lett 25(7):926\u2013930","journal-title":"IEEE Signal Process Lett"},{"issue":"1","key":"7808_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-022-00249-4","volume":"2022","author":"M Ju","year":"2022","unstructured":"Ju M, Xu Y, Ke D, Su K (2022) Masked multi-center angular margin loss for language recognition. EURASIP J Audio Speech Music Process 2022(1):1\u201322","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"7808_CR35","doi-asserted-by":"crossref","unstructured":"Li Z, Liu Y, Li L, Hong Q (2021) Additive phoneme-aware margin softmax loss for language recognition. In: Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 3276\u20133280","DOI":"10.21437\/Interspeech.2021-1167"},{"key":"7808_CR36","doi-asserted-by":"crossref","unstructured":"Pandey A, Wang DL (2020) Densely connected neural network with dilated convolutions for real-time speech enhancement in the time domain. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE), pp 6629\u20136633","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"7808_CR37","first-page":"100019","volume":"3","author":"F Deng","year":"2024","unstructured":"Deng F, Ming Y, Lyu B (2024) Cce-net: causal convolution embedding network for streaming automatic speech recognition. Int J Netw Dyn Intell 3:100019\u2013100019","journal-title":"Int J Netw Dyn Intell"},{"key":"7808_CR38","doi-asserted-by":"crossref","unstructured":"Ren J, Zhao H, Gao X et\u00a0al (2024) Research on fault diagnosis of rotating machinery based on multi-scale causal dilation convolution. In: 2024 7th International Conference on Pattern Recognition and Artificial Intelligence (PRAI) (IEEE), pp 922\u2013926","DOI":"10.1109\/PRAI62207.2024.10827805"},{"key":"7808_CR39","doi-asserted-by":"crossref","unstructured":"Wang HK, Long H, Liu X (2024) A multi-scale dilated causal convolution network based on data decomposition for the remaining useful life prediction of rolling bearings. In: 2024 4th International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) (IEEE), pp 602\u2013605","DOI":"10.1109\/CEI63587.2024.10871437"},{"key":"7808_CR40","doi-asserted-by":"crossref","unstructured":"De\u00a0Brabandere B, Neven D, Van\u00a0Gool L (2017) Semantic instance segmentation with a discriminative loss function. arXiv preprint arXiv:1708.02551","DOI":"10.1109\/CVPRW.2017.66"},{"key":"7808_CR41","unstructured":"Mao X, Li Q, Xie H et\u00a0al (2016) Multi-class generative adversarial networks with the l2 loss function. arXiv preprint arXiv:1611.04076 5:1057\u20137149"},{"key":"7808_CR42","doi-asserted-by":"crossref","unstructured":"Mingote V, Castan D, McLaren M, Nandwana MK, Gim\u00e9nez AO, Lleida E, Miguel A (2019) Language recognition using triplet neural network. In: Interspeech, pp 4025\u20134029","DOI":"10.21437\/Interspeech.2019-2437"},{"key":"7808_CR43","doi-asserted-by":"crossref","unstructured":"Cai W, Chen J, Li M (2018) Exploring the encoding layer and loss function in end-to-end speaker and language recognition system. arXiv preprint arXiv:1804.05160","DOI":"10.21437\/Odyssey.2018-11"},{"key":"7808_CR44","doi-asserted-by":"crossref","unstructured":"Huang J, Li Y, Tao J et\u00a0al (2018) Speech emotion recognition from variable-length inputs with triplet loss function. In: Interspeech, pp 3673\u20133677","DOI":"10.21437\/Interspeech.2018-1432"},{"key":"7808_CR45","doi-asserted-by":"publisher","first-page":"4806","DOI":"10.1109\/ACCESS.2019.2962617","volume":"8","author":"Y Ho","year":"2019","unstructured":"Ho Y, Wookey S (2019) The real-world-weight cross-entropy loss function: modeling the costs of mislabeling. IEEE access 8:4806\u20134813","journal-title":"IEEE access"},{"key":"7808_CR46","unstructured":"Mao A, Mohri M, Zhong Y (2023) Cross-entropy loss functions: theoretical analysis and applications. In: International conference on Machine learning (PMLR), pp 23803\u201323828"},{"key":"7808_CR47","doi-asserted-by":"crossref","unstructured":"Rezaei-Dastjerdehei MR, Mijani A, Fatemizadeh E (2020) Addressing imbalance in multi-label classification using weighted cross entropy loss function. In: 2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME) (IEEE), pp 333\u2013338","DOI":"10.1109\/ICBME51989.2020.9319440"},{"key":"7808_CR48","doi-asserted-by":"crossref","unstructured":"Cheng D, Gong Y, Zhou S et\u00a0al (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1335\u20131344","DOI":"10.1109\/CVPR.2016.149"},{"key":"7808_CR49","doi-asserted-by":"crossref","unstructured":"Ge W (2018) Deep metric learning with hierarchical triplet loss. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 269\u2013285","DOI":"10.1007\/978-3-030-01231-1_17"},{"issue":"12","key":"7808_CR50","doi-asserted-by":"publisher","first-page":"3180","DOI":"10.1109\/TMM.2020.2972125","volume":"22","author":"C Zhao","year":"2020","unstructured":"Zhao C, Lv X, Zhang Z et al (2020) Deep fusion feature representation learning with hard mining center-triplet loss for person re-identification. IEEE Trans Multimed 22(12):3180\u20133195","journal-title":"IEEE Trans Multimed"},{"key":"7808_CR51","doi-asserted-by":"crossref","unstructured":"Zhao Y, Jin Z, Qi G et\u00a0al (2018) An adversarial approach to hard triplet generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 501\u2013517","DOI":"10.1007\/978-3-030-01240-3_31"},{"key":"7808_CR52","doi-asserted-by":"crossref","unstructured":"Li J, Wang B, Zhi Y et\u00a0al (2021) Oriental language recognition (olr) 2020: Summary and analysis. arXiv preprint arXiv:2107.05365","DOI":"10.21437\/Interspeech.2021-2171"},{"key":"7808_CR53","doi-asserted-by":"crossref","unstructured":"Wang D, Li L, Tang D et al (2016) AP16-OL7: a multilingual database for oriental languages and a language recognition baseline. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Korea, Jeju, pp 1\u20135","DOI":"10.1109\/APSIPA.2016.7820796"},{"key":"7808_CR54","doi-asserted-by":"crossref","unstructured":"Tang Z, Wang D, Chen Y et al (2017) AP17-OLR challenge: data, plan, and baseline. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Kuala Lumpur, Malaysia, pp 749\u2013753","DOI":"10.1109\/APSIPA.2017.8282134"},{"key":"7808_CR55","doi-asserted-by":"crossref","unstructured":"Tang Z, Wang D, Song L (2019) AP19-OLR challenge: three tasks and their baselines. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (IEEE), pp 1917\u20131921","DOI":"10.1109\/APSIPAASC47483.2019.9023321"},{"key":"7808_CR56","doi-asserted-by":"crossref","unstructured":"Peng B, Zhu C, Zeng M et\u00a0al (2020) Data augmentation for spoken language understanding via pretrained language models. arXiv preprint arXiv:2004.13952","DOI":"10.21437\/Interspeech.2021-117"},{"key":"7808_CR57","unstructured":"Klco M, Novotn\u1ef3 O, Profant J et\u00a0al (2020) Phonexia SRO submission to OLR. Tech. rep"},{"key":"7808_CR58","unstructured":"Wang D, Ye S, Hu X, The royal flush system for AP20-OLR challenge. Tech Rep"},{"key":"7808_CR59","unstructured":"Zhou F, Ke C, Zhu M et\u00a0al, IBG AI language identification system for AP20-OLR. Tech rep"},{"key":"7808_CR60","unstructured":"Zhang J, Peng Y, Zhang H et\u00a0al, The NTU-XJU system for the AP20-OLR challenge. Tech rep"},{"key":"7808_CR61","doi-asserted-by":"publisher","first-page":"106921","DOI":"10.1016\/j.neunet.2024.106921","volume":"182","author":"C Chen","year":"2025","unstructured":"Chen C, Chen Y, Li W, Chen D (2025) Deep temporal representation learning for language identification. Neural Netw 182:106921","journal-title":"Neural Netw"},{"key":"7808_CR62","doi-asserted-by":"crossref","unstructured":"Lu X, Shen P, Tsao Y, Kawai H (2021) Unsupervised neural adaptation model based on optimal transport for spoken language identification. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE), pp 7213\u20137217","DOI":"10.1109\/ICASSP39728.2021.9414045"},{"key":"7808_CR63","doi-asserted-by":"crossref","unstructured":"Wang D, Ye S, Hu X, Li S, Xu X (2021) An End-to-End Dialect Identification System with Transfer Learning from a Multilingual Automatic Speech Recognition Model. In: Interspeech, vol\u00a01, pp 3266\u20133270","DOI":"10.21437\/Interspeech.2021-374"},{"key":"7808_CR64","unstructured":"Lu X, Shen P, Tsao Y, Kawai H (2022) Partial coupling of optimal transport for spoken language identification. arXiv preprint arXiv:2203.17036"},{"key":"7808_CR65","doi-asserted-by":"crossref","unstructured":"Kong T, Yin S, Zhang D et\u00a0al (2021) Dynamic multi-scale convolution for dialect identification. arxiv preprint arxiv:2108.07787","DOI":"10.21437\/Interspeech.2021-56"},{"key":"7808_CR66","doi-asserted-by":"crossref","unstructured":"Mishra J, Siddhartha S, Mahadeva\u00a0Prasanna SR (2022) Importance of excitation source and sequence learning towards spoken language identification task. In: National Conference on Communications (NCC), pp 190\u2013194","DOI":"10.1109\/NCC55593.2022.9806768"},{"key":"7808_CR67","doi-asserted-by":"publisher","first-page":"103055","DOI":"10.1016\/j.specom.2024.103055","volume":"158","author":"Z Li","year":"2024","unstructured":"Li Z, Xu Y, Ke D et al (2024) PLDE: a lightweight pooling layer for spoken language recognition. Speech Commun 158:103055","journal-title":"Speech Commun"},{"issue":"1","key":"7808_CR68","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s13636-023-00281-y","volume":"2023","author":"Z Li","year":"2023","unstructured":"Li Z, Xu Y, Ke D et al (2023) Three-stage training and orthogonality regularization for spoken language recognition. EURASIP J Audio Speech Music Process 2023(1):14","journal-title":"EURASIP J Audio Speech Music Process"},{"issue":"2","key":"7808_CR69","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1137\/18M1216134","volume":"1","author":"GC Linderman","year":"2019","unstructured":"Linderman GC, Steinerberger S (2019) Clustering with t-SNE, provably. SIAM J Math Data Sci 1(2):313\u2013332","journal-title":"SIAM J Math Data Sci"}],"updated-by":[{"DOI":"10.1007\/s11227-025-07881-9","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000}}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07808-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07808-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07808-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T04:24:02Z","timestamp":1761107042000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07808-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":69,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["7808"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07808-4","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"30 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2025","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11227-025-07881-9","URL":"https:\/\/doi.org\/10.1007\/s11227-025-07881-9","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1312"}}