{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:24:31Z","timestamp":1766298271454,"version":"3.37.3"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T00:00:00Z","timestamp":1674172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T00:00:00Z","timestamp":1674172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"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":["J AUDIO SPEECH MUSIC PROC."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recently, supervised speech separation has made great progress. However, limited by the nature of supervised training, most existing separation methods require ground-truth sources and are trained on synthetic datasets. This ground-truth reliance is problematic, because the ground-truth signals are usually unavailable in real conditions. Moreover, in many industry scenarios, the real acoustic characteristics deviate far from the ones in simulated datasets. Therefore, the performance usually degrades significantly when applying the supervised speech separation models to real applications. To address these problems, in this study, we propose a novel separation consistency training, termed SCT, to exploit the real-world unlabeled mixtures for improving cross-domain unsupervised speech separation in an iterative manner, by leveraging upon the complementary information obtained from heterogeneous (structurally distinct but behaviorally complementary) models. SCT follows a framework using two heterogeneous neural networks (HNNs) to produce high confidence pseudo labels of unlabeled real speech mixtures. These labels are then updated and used to refine the HNNs to produce more reliable consistent separation results for real mixture pseudo-labeling. To maximally utilize the large complementary information between different separation networks, a cross-knowledge adaptation is further proposed. Together with simulated dataset, those real mixtures with high confidence pseudo labels are then used to update the HNN separation models iteratively. In addition, we find that combing the heterogeneous separation outputs by a simple linear fusion can further slightly improve the final system performance. In this paper, we use cross-dataset to simulate the cross-domain situation in real-life. The term of \u201csource domain\u201d and \u201ctarget domain\u201d refer to the simulation set for model pre-training and the real unlabeled mixture for model adaptation. The proposed SCT is evaluated on both public reverberant English and anechoic Mandarin cross-domain separation tasks. Results show that, without any available ground-truth of target domain mixtures, the SCT can still significantly outperform our two strong baselines with up to 1.61 dB and 3.44 dB scale-invariant signal-to-noise ratio (SI-SNR) improvements, on the English and Mandarin cross-domain conditions, respectively.<\/jats:p>","DOI":"10.1186\/s13636-023-00273-y","type":"journal-article","created":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T02:26:33Z","timestamp":1674267993000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Heterogeneous separation consistency training for adaptation of unsupervised speech separation"],"prefix":"10.1186","volume":"2023","author":[{"given":"Jiangyu","family":"Han","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"}]}],"member":"297","published-online":{"date-parts":[[2023,1,20]]},"reference":[{"key":"273_CR1","doi-asserted-by":"crossref","unstructured":"J.R. Hershey, Z.\u00a0Chen, J.\u00a0Le\u00a0Roux, S.\u00a0Watanabe, in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Deep clustering: Discriminative embeddings for segmentation and separation (IEEE, 2016), pp. 31\u201335","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"273_CR2","doi-asserted-by":"crossref","unstructured":"D.\u00a0Yu, M.\u00a0Kolb\u00e6k, Z.H. Tan, J.\u00a0Jensen, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Permutation invariant training of deep models for speaker-independent multi-talker speech separation (IEEE, 2017), pp. 241\u2013245","DOI":"10.1109\/ICASSP.2017.7952154"},{"issue":"10","key":"273_CR3","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TASLP.2017.2726762","volume":"25","author":"M Kolb\u00e6k","year":"2017","unstructured":"M. Kolb\u00e6k, D. Yu, Z.H. Tan, J. Jensen, Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(10), 1901\u20131913 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"273_CR4","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Chen, Y.\u00a0Luo, N.\u00a0Mesgarani, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Deep attractor network for single-microphone speaker separation (IEEE, 2017), pp. 246\u2013250","DOI":"10.1109\/ICASSP.2017.7952155"},{"issue":"4","key":"273_CR5","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1109\/TASLP.2018.2795749","volume":"26","author":"Y Luo","year":"2018","unstructured":"Y. Luo, Z. Chen, N. Mesgarani, Speaker-independent speech separation with deep attractor network. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(4), 787\u2013796 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"273_CR6","doi-asserted-by":"crossref","unstructured":"Z.Q. Wang, J.\u00a0Le\u00a0Roux, J.R. Hershey, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Alternative objective functions for deep clustering (IEEE, 2018), pp. 686\u2013690","DOI":"10.1109\/ICASSP.2018.8462507"},{"issue":"10","key":"273_CR7","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"D. Wang, J. Chen, Supervised speech separation based on deep learning: An overview. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(10), 1702\u20131726 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"273_CR8","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2015","unstructured":"D.S. Williamson, Y. Wang, D. Wang, Complex ratio masking for monaural speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(3), 483\u2013492 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"273_CR9","doi-asserted-by":"crossref","unstructured":"K.\u00a0Tan, D.\u00a0Wang, in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Complex spectral mapping with a convolutional recurrent network for monaural speech enhancement (IEEE, 2019), pp. 6865\u20136869","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"273_CR10","unstructured":"H.S. Choi, J.H. Kim, J. Huh, A. Kim, J.W. Ha, K. Lee, Phase-aware speech enhancement with deep complex u-net. arXiv preprint arXiv:1903.03107 (2019)"},{"key":"273_CR11","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Hu, Y.\u00a0Liu, S.\u00a0Lv, M.\u00a0Xing, S.\u00a0Zhang, Y.\u00a0Fu, J.\u00a0Wu, B.\u00a0Zhang, L.\u00a0Xie, in Proc. Interspeech. DCCRN: Deep complex convolution recurrent network for phase-aware speech enhancement (IEEE, 2020), pp. 2472\u20132476","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"273_CR12","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Fu, J.\u00a0Wu, Y.\u00a0Hu, M.\u00a0Xing, L.\u00a0Xie, in 2021 IEEE Spoken Language Technology Workshop (SLT). DESNet: A multi-channel network for simultaneous speech dereverberation, enhancement and separation (IEEE, 2021), pp. 857\u2013864","DOI":"10.1109\/SLT48900.2021.9383604"},{"issue":"8","key":"273_CR13","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Y. Luo, N. Mesgarani, Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(8), 1256\u20131266 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"273_CR14","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Luo, Z.\u00a0Chen, T.\u00a0Yoshioka, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation (IEEE, 2020), pp. 46\u201350","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"273_CR15","doi-asserted-by":"crossref","unstructured":"J.\u00a0Zhang, C.\u00a0Zoril\u0103, R.\u00a0Doddipatla, J.\u00a0Barker, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). On end-to-end multi-channel time domain speech separation in reverberant environments (IEEE, 2020), pp. 6389\u20136393","DOI":"10.1109\/ICASSP40776.2020.9053833"},{"key":"273_CR16","doi-asserted-by":"crossref","unstructured":"J. Chen, Q. Mao, D. Liu, in Proc. Interspeech. Dual-path transformer network: Direct context-aware modeling for end-to-end monaural speech separation, pp. 2642\u20132646 (ISCA, Shanghai, China, 2020)","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"273_CR17","doi-asserted-by":"crossref","unstructured":"C.\u00a0Subakan, M.\u00a0Ravanelli, S.\u00a0Cornell, M.\u00a0Bronzi, J.\u00a0Zhong, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Attention is all you need in speech separation (IEEE, 2021), pp. 21\u201325","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"273_CR18","doi-asserted-by":"crossref","unstructured":"J.\u00a0Han, X.\u00a0Zhou, Y.\u00a0Long, Y.\u00a0Li, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Multi-channel target speech extraction with channel decorrelation and target speaker adaptation (IEEE, 2021), pp. 6094\u20136098","DOI":"10.1109\/ICASSP39728.2021.9414244"},{"key":"273_CR19","doi-asserted-by":"crossref","unstructured":"J. Han, W. Rao, Y. Wang, Y. Long, in Proc. Interspeech. Improving channel decorrelation for multi-channel target speech extraction, pp. 1847\u20131851 (ISCA, Brno, Czech, 2021)","DOI":"10.21437\/Interspeech.2021-298"},{"key":"273_CR20","doi-asserted-by":"crossref","unstructured":"J.\u00a0Han, W.\u00a0Rao, Y.\u00a0Long, J.\u00a0Liang, in 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Attention-based scaling adaptation for target speech extraction (IEEE, 2021), pp. 658\u2013662","DOI":"10.1109\/ASRU51503.2021.9687903"},{"key":"273_CR21","doi-asserted-by":"crossref","unstructured":"J. Chen, Q. Mao, D. Liu, in Proc. Interspeech. On synthesis for supervised monaural speech separation in time domain, pp. 2627\u20132631 (ISCA, Shanghai, China, 2020)","DOI":"10.21437\/Interspeech.2020-1150"},{"key":"273_CR22","doi-asserted-by":"crossref","unstructured":"Z.Q. Wang, D.\u00a0Wang, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Count and separate: Incorporating speaker counting for continuous speaker separation (IEEE, 2021), pp. 11\u201315","DOI":"10.1109\/ICASSP39728.2021.9414677"},{"key":"273_CR23","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Luo, Z.\u00a0Chen, C.\u00a0Han, C.\u00a0Li, T.\u00a0Zhou, N.\u00a0Mesgarani, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rethinking the separation layers in speech separation networks (IEEE, 2021), pp. 1\u20135","DOI":"10.1109\/ICASSP39728.2021.9414176"},{"key":"273_CR24","doi-asserted-by":"crossref","unstructured":"G.P. Yang, C.I. Tuan, H.Y. Lee, L.s. Lee, in Proc. Interspeech. Improved speech separation with time-and-frequency cross-domain joint embedding and clustering, pp. 1363\u20131367 (ISCA, Graz, Austria, 2019)","DOI":"10.21437\/Interspeech.2019-2181"},{"issue":"5","key":"273_CR25","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1109\/TASLP.2016.2536478","volume":"24","author":"XL Zhang","year":"2016","unstructured":"X.L. Zhang, D. Wang, A deep ensemble learning method for monaural speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(5), 967\u2013977 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"273_CR26","doi-asserted-by":"crossref","unstructured":"H. Shi, L. Wang, S. Li, C. Ding, M. Ge, N. Li, J. Dang, H. Seki, in Proc. Interspeech. Singing voice extraction with attention-based spectrograms fusion, pp. 2412\u20132416 (ISCA, Shanghai, China, 2020)","DOI":"10.21437\/Interspeech.2020-1043"},{"key":"273_CR27","doi-asserted-by":"crossref","unstructured":"H.\u00a0Shi, L.\u00a0Wang, M.\u00a0Ge, S.\u00a0Li, J.\u00a0Dang, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Spectrograms fusion with minimum difference masks estimation for monaural speech dereverberation (IEEE, 2020), pp. 7544\u20137548","DOI":"10.1109\/ICASSP40776.2020.9054661"},{"key":"273_CR28","unstructured":"S. Wisdom, E. Tzinis, H. Erdogan, R.J. Weiss, K. Wilson, J.R. Hershey, in Advances in Neural Information Processing Systems. Unsupervised sound separation using mixture invariant training (NeurIPS, Vancouver, Canada, 2020)"},{"key":"273_CR29","doi-asserted-by":"crossref","unstructured":"S. Wisdom, A. Jansen, R.J. Weiss, H. Erdogan, J.R. Hershey, in Workshop on Applications of Signal Processing to Audio and Acoustics. Sparse, efficient, and semantic mixture invariant training: Taming in-the-wild unsupervised sound separation (IEEE, New Paltz, USA, 2021)","DOI":"10.1109\/WASPAA52581.2021.9632714"},{"key":"273_CR30","doi-asserted-by":"crossref","unstructured":"A.\u00a0Sivaraman, S.\u00a0Wisdom, H.\u00a0Erdogan, J.R. Hershey, Adapting speech separation to real-world meetings using mixture invariant training. arXiv preprint arXiv:2110.10739 (2021)","DOI":"10.1109\/ICASSP43922.2022.9747855"},{"key":"273_CR31","doi-asserted-by":"crossref","unstructured":"J. Zhang, C. Zorila, R. Doddipatla, J. Barker, in Proc. Interspeech. Teacher-student MixIT for unsupervised and semi-supervised speech separation, pp. 3495\u20133499 (ISCA, Brno, Czech, 2021)","DOI":"10.21437\/Interspeech.2021-1243"},{"key":"273_CR32","doi-asserted-by":"crossref","unstructured":"R. Gao, K. Grauman, in Proceedings of the IEEE\/CVF International Conference on Computer Vision. Co-separating sounds of visual objects, pp. 3879\u20133888 (IEEE, Seoul, Korea, 2019)","DOI":"10.1109\/ICCV.2019.00398"},{"key":"273_CR33","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Hoshen, in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Towards unsupervised single-channel blind source separation using adversarial pair unmix-and-remix (IEEE, 2019), pp. 3272\u20133276","DOI":"10.1109\/ICASSP.2019.8682375"},{"key":"273_CR34","doi-asserted-by":"crossref","unstructured":"M.W. Lam, J.\u00a0Wang, D.\u00a0Su, D.\u00a0Yu, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Mixup-breakdown: a consistency training method for improving generalization of speech separation models (IEEE, 2020), pp. 6374\u20136378","DOI":"10.1109\/ICASSP40776.2020.9054719"},{"key":"273_CR35","doi-asserted-by":"crossref","unstructured":"J. Han, Y. Long, L. Burge, J. Cernocky, in 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). DPCCN: Densely-connected pyramid complex convolutional network for robust speech separation and extraction, pp. 7292-7296","DOI":"10.1109\/ICASSP43922.2022.9747340"},{"key":"273_CR36","unstructured":"J.\u00a0Cosentino, M.\u00a0Pariente, S.\u00a0Cornell, A.\u00a0Deleforge, E.\u00a0Vincent, Librimix: An open-source dataset for generalizable speech separation. arXiv preprint arXiv:2005.11262 (2020)"},{"key":"273_CR37","doi-asserted-by":"crossref","unstructured":"M.\u00a0Maciejewski, G.\u00a0Wichern, E.\u00a0McQuinn, J.\u00a0Le\u00a0Roux, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). WHAMR!: Noisy and reverberant single-channel speech separation (IEEE, 2020), pp. 696\u2013700","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"273_CR38","doi-asserted-by":"crossref","unstructured":"J.\u00a0Le\u00a0Roux, S.\u00a0Wisdom, H.\u00a0Erdogan, J.R. Hershey, in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Sdr\u2013half-baked or well done? (IEEE, 2019), pp. 626\u2013630","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"273_CR39","doi-asserted-by":"crossref","unstructured":"J.\u00a0Heitkaemper, D.\u00a0Jakobeit, C.\u00a0Boeddeker, L.\u00a0Drude, R.\u00a0Haeb-Umbach, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Demystifying TasNet: A dissecting approach (IEEE, 2020), pp. 6359\u20136363","DOI":"10.1109\/ICASSP40776.2020.9052981"},{"key":"273_CR40","doi-asserted-by":"crossref","unstructured":"S.\u00a0Sonning, C.\u00a0Sch\u00fcldt, H.\u00a0Erdogan, S.\u00a0Wisdom, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Performance study of a convolutional time-domain audio separation network for real-time speech denoising (IEEE, 2020), pp. 831\u2013835","DOI":"10.1109\/ICASSP40776.2020.9053846"},{"key":"273_CR41","doi-asserted-by":"crossref","unstructured":"T.\u00a0Ochiai, M.\u00a0Delcroix, R.\u00a0Ikeshita, K.\u00a0Kinoshita, T.\u00a0Nakatani, S.\u00a0Araki, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Beam-TasNet: Time-domain audio separation network meets frequency-domain beamformer (IEEE, 2020), pp. 6384\u20136388","DOI":"10.1109\/ICASSP40776.2020.9053575"},{"key":"273_CR42","doi-asserted-by":"crossref","unstructured":"T.\u00a0von Neumann, K.\u00a0Kinoshita, L.\u00a0Drude, C.\u00a0Boeddeker, M.\u00a0Delcroix, T.\u00a0Nakatani, R.\u00a0Haeb-Umbach, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). End-to-end training of time domain audio separation and recognition (IEEE, 2020), pp. 7004\u20137008","DOI":"10.1109\/ICASSP40776.2020.9053461"},{"key":"273_CR43","doi-asserted-by":"crossref","unstructured":"C.\u00a0Lea, R.\u00a0Vidal, A.\u00a0Reiter, G.D. Hager, in European Conference on Computer Vision. Temporal convolutional networks: A unified approach to action segmentation (Springer, 2016), pp. 47\u201354","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"273_CR44","doi-asserted-by":"crossref","unstructured":"C. Lea, M.D. Flynn, R. Vidal, A. Reiter, G.D. Hager, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Temporal convolutional networks for action segmentation and detection, pp. 156\u2013165 (IEEE, Hawaii, USA, 2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"273_CR45","unstructured":"S.\u00a0Bai, J.Z. Kolter, V.\u00a0Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"273_CR46","doi-asserted-by":"crossref","unstructured":"O.\u00a0Ronneberger, P.\u00a0Fischer, T.\u00a0Brox, in International Conference on Medical image computing and computer-assisted intervention. U-net: Convolutional networks for biomedical image segmentation (Springer, 2015), pp. 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"273_CR47","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, in Proceedings of the IEEE conference on computer vision and pattern recognition. Densely connected convolutional networks, pp. 4700\u20134708 (IEEE, Hawaii, USA, 2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"273_CR48","doi-asserted-by":"crossref","unstructured":"H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, in Proceedings of the IEEE conference on computer vision and pattern recognition. Pyramid scene parsing network, pp. 2881\u20132890 (IEEE, Hawaii, USA, 2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"273_CR49","doi-asserted-by":"crossref","unstructured":"V.\u00a0Panayotov, G.\u00a0Chen, D.\u00a0Povey, S.\u00a0Khudanpur, in 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP). Librispeech: an asr corpus based on public domain audio books (IEEE, 2015), pp. 5206\u20135210","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"273_CR50","unstructured":"Aishell2Mix. https:\/\/github.com\/jyhan03\/icassp22-dataset. Accessed 18 Jan 2023"},{"key":"273_CR51","doi-asserted-by":"crossref","unstructured":"H.\u00a0Bu, J.\u00a0Du, X.\u00a0Na, B.\u00a0Wu, H.\u00a0Zheng, in 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA). AISHELL-1: An open-source mandarin speech corpus and a speech recognition baseline (IEEE, 2017), pp. 1\u20135","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"273_CR52","unstructured":"N.\u00a0Whitehead, A.\u00a0Fit-Florea, Precision & performance: Floating point and IEEE 754 compliance for nvidia gpus. rn (A+ B) 21(1), 18749\u201319424 (2011)"},{"key":"273_CR53","unstructured":"THOP. https:\/\/github.com\/Lyken17\/pytorch-OpCounter. Accessed 18 Jan 2023"},{"key":"273_CR54","unstructured":"D.P. Kingma, J.\u00a0Ba, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"273_CR55","unstructured":"DPCCN. https:\/\/github.com\/jyhan03\/dpccn. Accessed 18 Jan 2023"},{"issue":"4","key":"273_CR56","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"E. Vincent, R. Gribonval, C. F\u00e9votte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-023-00273-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-023-00273-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-023-00273-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T02:33:24Z","timestamp":1674268404000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-023-00273-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,20]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["273"],"URL":"https:\/\/doi.org\/10.1186\/s13636-023-00273-y","relation":{},"ISSN":["1687-4722"],"issn-type":[{"type":"electronic","value":"1687-4722"}],"subject":[],"published":{"date-parts":[[2023,1,20]]},"assertion":[{"value":"30 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6"}}