{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:20:55Z","timestamp":1776885655677,"version":"3.51.2"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T00:00:00Z","timestamp":1729296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176102"],"award-info":[{"award-number":["62176102"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276076"],"award-info":[{"award-number":["62276076"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"DOI":"10.1186\/s13636-024-00375-1","type":"journal-article","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T02:01:46Z","timestamp":1729303306000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SVQ-MAE: an efficient speech pre-training framework with constrained computational resources"],"prefix":"10.1186","volume":"2024","author":[{"given":"Xuyi","family":"Zhuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukun","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,19]]},"reference":[{"key":"375_CR1","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu et al., Momentum contrast for unsupervised visual representation learning. in IEEE Conference on Computer Vision and Pattern Recognition, Seattle, pp. 9726\u20139735 (2020). IEEE","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"375_CR2","unstructured":"K. He, X. Chen, S. Xie et al., Masked autoencoders are scalable vision learners. in IEEE Conference on Computer Vision and Pattern Recognition, New Orleans, pp. 15979\u201315988 (2020). IEEE"},{"key":"375_CR3","unstructured":"T. Chen, S. Kornblith, M. Norouzi et al., A simple framework for contrastive learning of visual representations. in International Conference on Machine Learning, Vienna, pp. 1597\u20131607 (2020). PMLR"},{"key":"375_CR4","unstructured":"J.B. Grill, F. Strub, F. Altch\u00e9 et al., Bootstrap your own latent-a new approach to self-supervised learning. Advances in Neural Information Processing Systems 33, 21271\u201321284 (2020)"},{"key":"375_CR5","doi-asserted-by":"crossref","unstructured":"X. Chen, K. He, Exploring simple siamese representation learning. in IEEE Conference on Computer Vision and Pattern Recognition, Nashville, pp. 15750\u201315758 (2021). IEEE","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"375_CR6","doi-asserted-by":"crossref","unstructured":"S. Chen, C. Wang, Z. Chen et al., Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE Journal of Selected Topics in Signal Processing 16(6), 1505\u20131518 (2022)","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"375_CR7","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"W.N. Hsu, B. Bolte, Y.H.H. Tsai et al., A. Mohamed, Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Transactions on Audio, Speech, and Language Processing\u00a029, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"375_CR8","unstructured":"A. Baevski, W.N. Hsu, Q. Xu et al., Data2vec: A general framework for self-supervised learning in speech, vision and language. in International Conference on Machine Learning, Baltimore, pp. 2640\u20133498 (2022). PMLR"},{"key":"375_CR9","unstructured":"A. Vaswani, N. Shazeer, N. Parmar et al., Attention is all you need. in NIPS, Long Beach, pp. 1049\u20135258 (2017). PMLR"},{"key":"375_CR10","unstructured":"H. Bao, L. Dong, F. Wei, Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"375_CR11","unstructured":"A. Baevski, Y. Zhou, A. Mohamed et al., wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems 33, 12449\u201312460 (2020)"},{"key":"375_CR12","doi-asserted-by":"crossref","unstructured":"M. Caron, P. Bojanowski, A. Joulin et al., Deep clustering for unsupervised learning of visual features. in European Conference on Computer Vision, Munich, pp. 139\u2013156 (2018). Springer","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"375_CR13","doi-asserted-by":"crossref","unstructured":"S. Yang, P. Chi, Y. Chuang et al., Superb: Speech Processing Universal Performance Benchmark. in Proc. Interspeech, Brno, pp. 1194\u20131198 (2021). ISCA","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"375_CR14","unstructured":"H. Xu, J. Li, A. Baevski et al., Masked autoencoders that listen. in NEURIPS, New Orleans, pp. 1049\u20135258 (2022). PMLR"},{"key":"375_CR15","doi-asserted-by":"crossref","unstructured":"A. Baade, P. Peng, D. Harwath, Mae-ast: Masked autoencoding audio spectrogram transformer. in Proc. Interspeech, Incheon, pp. 2438\u20132442 (2022). ISCA","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"375_CR16","doi-asserted-by":"crossref","unstructured":"A. Liu, S. Yang, P. Chi et al., Mockingjay: Unsupervised speech representation learning with deep bidirectional transformer encoders. in IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, pp. 6419\u20136423 (2020). IEEE","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"375_CR17","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1109\/TASLP.2021.3095662","volume":"29","author":"AT Liu","year":"2021","unstructured":"A. Liu, S. Li, H. Lee, Tera: Self-supervised learning of transformer encoder representation for speech. IEEE\/ACM Transactions on Audio, Speech, and Language Processing\u00a029, 2351\u20132366 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"375_CR18","doi-asserted-by":"crossref","unstructured":"S. Ling, Y. Liu, J. Salazar et al., Deep contextualized acoustic representations for semi-supervised speech recognition. in IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, pp. 6429\u20136433 (2020). IEEE","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"375_CR19","unstructured":"S. Ling, Y. Liu, Decoar 2.0: Deep contextualized acoustic representations with vector quantization. arXiv preprint arXiv:2012.06659 (2020)"},{"key":"375_CR20","unstructured":"A.v.d. Oord, Y. Li, O. Vinyals, Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"375_CR21","doi-asserted-by":"crossref","unstructured":"S. Schneider, A. Baevski, R. Collobert et al., wav2vec: Unsupervised pre-training for speech recognition. in Proc. Interspeech, Graz, pp. 3465\u20133469 (2019). ISCA","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"375_CR22","unstructured":"A. Baevski, S. Schneider, M. Auli, vq-wav2vec: Self-supervised learning of discrete speech representations. arXiv preprint arXiv:1910.05453 (2019)"},{"key":"375_CR23","doi-asserted-by":"crossref","unstructured":"H. Chang, S. Yang, H. Lee. Distilhubert: Speech representation learning by layer-wise distillation of hidden-unit bert. in IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, pp. 7087\u20137091 (2022). IEEE","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"375_CR24","doi-asserted-by":"crossref","unstructured":"S. Pascual, M. Ravanelli, J. Serra et al., Learning problem-agnostic speech representations from multiple self-supervised tasks. in Proc. Interspeech, Graz, pp. 161-165 (2019). ISCA","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"375_CR25","doi-asserted-by":"crossref","unstructured":"M. Ravanelli, J. Zhong, S. Pascual et al., Multi-task self-supervised learning for robust speech recognition. in IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, pp. 6989\u20136993 (2020). IEEE","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"375_CR26","unstructured":"C. Wang, Y. Wu, Y. Qian et al., Unispeech: Unified speech representation learning with labeled and unlabeled data. in International Conference on Machine Learning, Vienna, pp. 10937\u201310947 (2021). PMLR"},{"key":"375_CR27","doi-asserted-by":"crossref","unstructured":"J. Bai, B. Li, Y. Zhang et al., Joint unsupervised and supervised training for multilingual asr. in IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, pp. 6402\u20136406 (2022). IEEE","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"375_CR28","unstructured":"M. Gutmann, A. Hyv\u00e4rinen, Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. in International Conference on Artificial Intelligence and Statistics, Sardinia, pp. 297\u2013304 (2010). Springer"},{"key":"375_CR29","unstructured":"A.v.d. Oord, Y. Li, O. Vinyals, Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"375_CR30","doi-asserted-by":"crossref","unstructured":"V. Panayotov, G. Chen, D. Povey et al., Librispeech: An ASR corpus based on public domain audio books. in IEEE International Conference on Acoustics, Speech and Signal Processing, Brisbane, pp. 5206\u20135210 (2015). IEEE","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"375_CR31","doi-asserted-by":"crossref","unstructured":"C.K. Reddy, V. Gopal, R. Cutler et al., The interspeech 2020 deep noise suppression challenge: Datasets, subjective testing framework, and challenge results. in Proc. Interspeech, Beijing, pp. 2492\u20132496 (2020). ISCA","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"375_CR32","unstructured":"P. Warden, Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 (2018)"},{"issue":"4","key":"375_CR33","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"C. Busso, M. Bulut, C.C. Lee el al., IEMOCAP: Interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"375_CR34","doi-asserted-by":"crossref","unstructured":"A. Nagrani, J.S. Chung, A. Zisserman, Voxceleb: A large-scale speaker identification dataset. in Proc. Interspeech, Stockholm, pp. 2616\u20132620 (2017). ISCA","DOI":"10.21437\/Interspeech.2017-950"},{"key":"375_CR35","doi-asserted-by":"crossref","unstructured":"H. Bu, J. Du, X. Na et al., Aishell-1: An open-source mandarin speech corpus and a speech recognition baseline. in Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O systems and Assessment, Seoul, pp. 58-62. (2017). IEEE","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"375_CR36","doi-asserted-by":"crossref","unstructured":"M. Ott, S. Edunov, A. Baevski et al., Fairseq: A fast, extensible toolkit for sequence modeling. in Conference of the North-American-Chapter of the Association-for-Computational-Linguistics-Human Language Technologies, Minneapolis, pp. 48\u201353 (2019). ACL","DOI":"10.18653\/v1\/N19-4009"},{"key":"375_CR37","unstructured":"D.P. Kingma, J. Ba, Adam: A method for stochastic optimization. in Proc. ICLR, San Diego. (2015). OpenReview"},{"key":"375_CR38","doi-asserted-by":"crossref","unstructured":"A.H. Liu, Y.A. Chung, J. Glass, Non-autoregressive predictive coding for learning speech representations from local dependencies. in Proc. Interspeech, Brno, pp. 3730-3734 (2021). ISCA","DOI":"10.21437\/Interspeech.2021-349"},{"key":"375_CR39","unstructured":"Y.A. Chung, W.N. Hsu, H. Tang et al., An unsupervised autoregressive model for speech representation learning. in Proc. Interspeech, Graz, pp. 146-150 (2022). ISCA"},{"key":"375_CR40","doi-asserted-by":"crossref","unstructured":"Y.A. Chung, H. Tang, J. Glass, Vector-quantized autoregressive predictive coding. in Proc. Interspeech, Beijing, pp. 3760-3764 (2020). ISCA","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"375_CR41","doi-asserted-by":"crossref","unstructured":"P. Peng, D. Harwath, Fast-slow transformer for visually grounding speech. in IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, pp. 7727\u20137731 (2022). IEEE","DOI":"10.1109\/ICASSP43922.2022.9747103"},{"key":"375_CR42","unstructured":"P. Peng, D. Harwath, Self-supervised representation learning for speech using visual grounding and masked language modeling. in AAAI, Vancouver. (2022). AAAI"},{"key":"375_CR43","doi-asserted-by":"crossref","unstructured":"W.N. Hsu, D. Harwath, T. Miller et al., Text-free image-to-speech synthesis using learned segmental units. in ACL, Bangkok, pp. 5284\u20135300 (2021). ACL","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"375_CR44","unstructured":"A. Fan, E. Grave, A. Joulin, Reducing transformer depth on demand with structured dropout. in Proc. ICLR, Addis Ababa. (2022). OpenReview"},{"key":"375_CR45","doi-asserted-by":"crossref","unstructured":"G. Huang, Y. Sun, Z. Liu, D. Sedra et al., Deep networks with stochastic depth. in European Conference on Computer Vision, Amsterdam, pp. 646\u2013661 (2016). Springer","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"375_CR46","doi-asserted-by":"crossref","unstructured":"D.S. Park, W. Chan, Y. Zhang et al., SpecAugment: A simple data augmentation method for automatic speech recognition. in Proc. Interspeech, Graz, pp. 2613\u20132617 (2019). ISCA","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"375_CR47","doi-asserted-by":"crossref","unstructured":"Z. Guo, S. Zhuang, I. McLoughlin et al., Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. in Proc. Interspeech, Incheon, pp. 2063\u20132067 (2022). ISCA","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"375_CR48","doi-asserted-by":"crossref","unstructured":"Z. Yao, D. Wu, X. Wang et al., WeNet: Production oriented streaming and non-streaming end-to-end speech recognition toolkit. in Proc. Interspeech, Brno, pp. 4054-4058 (2021). ISCA","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"375_CR49","doi-asserted-by":"crossref","unstructured":"Z. Tian, J. Yi, J. Tao et al., Spike-triggered non-autoregressive transformer for end-to-end speech recognition. in Proc. Interspeech, Beijing, pp. 5026-5030 (2020). ISCA","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"375_CR50","doi-asserted-by":"crossref","unstructured":"Y. Fujita, S. Watanabe, M. Omachi et al., Insertion-based modeling for end-to-end automatic speech recognition. in Proc. Interspeech, Beijing, pp. 3660-3664 (2020). ISCA","DOI":"10.21437\/Interspeech.2020-1619"},{"key":"375_CR51","doi-asserted-by":"crossref","unstructured":"Y. Bai, J. Yi, J. Tao et al., Listen attentively, and spell once: Whole sentence generation via a non-autoregressive architecture for low-latency speech recognition. in Proc. Interspeech, Beijing, pp. 3381\u20133385 (2020). ISCA","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"375_CR52","doi-asserted-by":"crossref","unstructured":"X. Song, Z. Wu, Y. Huang et al., Non-autoregressive transformer ASR with CTC-enhanced decoder input. in IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, pp. 5894\u20135898 (2021). IEEE","DOI":"10.1109\/ICASSP39728.2021.9414694"},{"key":"375_CR53","doi-asserted-by":"crossref","unstructured":"Y. Qian, X. Zhuang, Z. Zhang et al., Non-autoregressive speech recognition with error correction module. in Proc. APSIPA, Bangkok, pp. 1104\u20131109 (2022). ACM","DOI":"10.23919\/APSIPAASC55919.2022.9980031"},{"key":"375_CR54","doi-asserted-by":"crossref","unstructured":"C. Zhang, Y. Liu, T. Zhang et al., Non-autoregressive transformer with unified bidirectional decoder for automatic speech recognition. in IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, pp. 6527\u20136531 (2022). IEEE","DOI":"10.1109\/ICASSP43922.2022.9746903"},{"key":"375_CR55","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1109\/LSP.2022.3152128","volume":"29","author":"Z Tian","year":"2022","unstructured":"Z. Tian, J. Yi, J. Tao et al., Hybrid autoregressive and non-autoregressive transformer models for speech recognition. IEEE Signal Processing Letter\u00a029, 762\u2013766 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"375_CR56","unstructured":"D. Wang, X. Zhang, THCHS-30: A free Chinese speech corpus. arXiv preprint arXiv:1512.01882 (2015)"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-024-00375-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-024-00375-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-024-00375-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:24:45Z","timestamp":1732919085000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-024-00375-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,19]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["375"],"URL":"https:\/\/doi.org\/10.1186\/s13636-024-00375-1","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,19]]},"assertion":[{"value":"11 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"55"}}