{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T09:13:20Z","timestamp":1723022000211},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T00:00:00Z","timestamp":1609891200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s00530-020-00740-y","type":"journal-article","created":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T09:04:14Z","timestamp":1609923854000},"page":"271-286","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multichannel speech separation using hybrid GOMF and enthalpy-based deep neural networks"],"prefix":"10.1007","volume":"27","author":[{"given":"Yannam Vasantha","family":"Koteswararao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. B. Rama","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,6]]},"reference":[{"issue":"10","key":"740_CR1","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang, D., Chen, J.: 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."},{"key":"740_CR2","doi-asserted-by":"crossref","unstructured":"Ding, Y., Xu, Y., Zhang, S., Cong, Y., Wang, L.: Self-Supervised Learning for Audio-Visual Speaker Diarization, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 4367\u20134371","DOI":"10.1109\/ICASSP40776.2020.9054376"},{"key":"740_CR3","doi-asserted-by":"crossref","unstructured":"Bahmaninezhad, F., Jian W., Rongzhi G., Shi-Xiong Z., Yong X., Meng Y., Dong Y.: A comprehensive study of speech separation: spectrogram vs waveform separation. arXiv preprint arXiv: 1905.07497 (2019)","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"740_CR4","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.knosys.2018.07.041","volume":"161","author":"N Majumder","year":"2018","unstructured":"Majumder, N., Hazarika, D., Gelbukh, A., Cambria, E., Poria, S.: Multimodal sentiment analysis using hierarchical fusion with context modeling. Knowl.-Based Syst. 161, 124\u2013133 (2018)","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"740_CR5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/JSTSP.2019.2901664","volume":"13","author":"S Chakrabarty","year":"2019","unstructured":"Chakrabarty, S., Habets, E.A.: Multi-speaker doa estimation using deep convolutional networks trained with noise signals. IEEE J. Select. Topics Signal Process. 13(1), 8\u201321 (2019)","journal-title":"IEEE J. Select. Topics Signal Process."},{"key":"740_CR6","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition, IEEE transactions on pattern analysis and machine intelligence, 2018","DOI":"10.1109\/TPAMI.2018.2889052"},{"issue":"8","key":"740_CR7","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Luo, Y., Mesgarani, N.: 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":"740_CR8","doi-asserted-by":"crossref","unstructured":"Luo, Y., Han, C., Mesgarani, N., Ceolini, E., Liu, S.C.: (2019). FaSNet: Low-latency adaptive beamforming for multi-microphone audio processing. In 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (pp. 260\u2013267). IEEE","DOI":"10.1109\/ASRU46091.2019.9003849"},{"key":"740_CR9","unstructured":"Rongzhi G., Shi-Xiong Z.: Multi-modal Multi-channel Target Speech Separation. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2020"},{"issue":"4","key":"740_CR10","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1109\/TASLP.2018.2795749","volume":"26","author":"Yi Luo","year":"2018","unstructured":"Luo, Yi., Chen, Z., Mesgarani, N.: 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":"740_CR11","doi-asserted-by":"crossref","unstructured":"Fan, C., Jianhua T., Bin, L., Jiangyan Y., Zhengqi W.: Gated recurrent fusion of spatial and spectral features for multi-channel speech separation with deep embedding representations. In Proc. Interspeech, vol. 2020. 2020","DOI":"10.21437\/Interspeech.2020-1548"},{"issue":"5","key":"740_CR12","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1109\/TASLP.2019.2907015","volume":"27","author":"K Shimada","year":"2019","unstructured":"Shimada, K., Bando, Y., Mimura, M., Itoyama, K., Yoshii, K., Kawahara, T.: Unsupervised speech enhancement based on multichannel NMF-informed beamforming for noise-robust automatic speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(5), 960\u2013971 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"740_CR13","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/TASLP.2019.2892412","volume":"27","author":"X Li","year":"2019","unstructured":"Li, X., Girin, L., Gannot, S., Horaud, R.: Multichannel speech separation and enhancement using the convolutive transfer function. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(3), 645\u2013659 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"740_CR14","doi-asserted-by":"crossref","unstructured":"Gu, R., Shi-Xiong Z., Lianwu C., Yong X., Meng Y., Dan S., Yuexian Z., Dong Y.: Enhancing End-to-End Multi-Channel Speech Separation Via Spatial Feature Learning. In ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7319\u20137323. IEEE, 2020","DOI":"10.1109\/ICASSP40776.2020.9053092"},{"issue":"8","key":"740_CR15","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Yi Luo","year":"2019","unstructured":"Luo, Yi., Mesgarani, N.: Conv-tasnet: Surpassing ideal time\u2013frequency 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":"740_CR16","unstructured":"Luo, Y., Zhuo C., Nima M., Takuya Yoshioka.: End-to-end microphone permutation and number invariant multi-channel speech separation. In ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6394\u20136398. IEEE, 2020."},{"key":"740_CR17","doi-asserted-by":"crossref","unstructured":"Gu, R., Shi-Xiong Z., Yong X., Lianwu C., Yuexian Z., Dong Y.: Multi-modal multi-channel target speech separation. IEEE J. Select. Topics Signal Process. (2020).","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"740_CR18","doi-asserted-by":"publisher","first-page":"168104","DOI":"10.1109\/ACCESS.2019.2954120","volume":"7","author":"S Seki","year":"2019","unstructured":"Seki, S., Kameoka, H., Li, Li., Toda, T., Takeda, K.: Underdetermined source separation based on generalized multichannel variationalautoencoder. IEEE Access 7, 168104\u2013168115 (2019)","journal-title":"IEEE Access"},{"key":"740_CR19","doi-asserted-by":"crossref","unstructured":"Yan, C., Biao G., Yuxuan W., Yue G. Deep multi-view enhancement hashing for image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. (2020).","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"740_CR20","doi-asserted-by":"crossref","unstructured":"Yan, C., Biyao S., Hao Z., Ruixin N., Yongdong Z., Feng X.: 3d room layout estimation from a single rgb image. IEEE Trans. Multimed. (2020).","DOI":"10.1109\/TMM.2020.2967645"},{"key":"740_CR21","unstructured":"Yan, C., Zhisheng L., Yongbing Z., Yutao L., Xiangyang J., Yongdong Z.: Depth image denoising using nuclear norm and learning graph model. arXiv preprint:2008.03741(2020)."},{"key":"740_CR22","unstructured":"Yicheng, D., Kouhei, S.: Semi-supervised Multichannel Speech Separation Based on a Phone- and Speaker-Aware Deep Generative Model of Speech Spectrograms, National Institute of Advanced Industrial Science and Technology, 2020."},{"issue":"3","key":"740_CR23","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TASL.2009.2031510","volume":"18","author":"A Ozerov","year":"2010","unstructured":"Ozerov, A., Fevotte, C.: Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation. IEEE Trans. Audio Speech Lang. Process. 18(3), 550\u2013563 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"58","key":"740_CR24","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.csl.2019.05.008","volume":"1","author":"Y Saito","year":"2019","unstructured":"Saito, Y., Takamichi, S., Saruwatari, H.: Vocoder-free text-to-speech synthesis incorporating generative adversarial networks using low-\/multi-frequency STFT amplitude spectra. Comput. Speech Lang. 1(58), 347\u2013363 (2019)","journal-title":"Comput. Speech Lang."},{"key":"740_CR25","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/TASLP.2019.2948770","volume":"28","author":"Y Mitsufuji","year":"2020","unstructured":"Mitsufuji, Y., Uhlich, S., Takamune, N., Kitamura, D., Koyama, S., Saruwatari, H.: Multichannel non-negative matrix factorization using banded spatial covariance matrices in wavenumber domain. IEEE Trans. Audio Speech Lang. Process. 28, 49\u201360 (2020)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"740_CR26","doi-asserted-by":"publisher","first-page":"1778","DOI":"10.1109\/TASLP.2020.2998279","volume":"28","author":"Z-Q Wang","year":"2020","unstructured":"Wang, Z.-Q., Wang, P., Wang, D.: Complex spectral mapping for single- and multi-channel speech enhancement and robust ASR. IEEE Trans. Audio Speech Lang. Process. 28, 1778\u20131787 (2020)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"740_CR27","unstructured":"Yoshiki, M.T., Tatsuya K.: Consistency-aware multi-channel speech enhancement using deep neural networks. In ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 821\u2013825. IEEE, 2020."},{"issue":"106","key":"740_CR28","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.specom.2018.11.006","volume":"1","author":"AM Martinez","year":"2019","unstructured":"Martinez, A.M., Gerlach, L., Pay\u00e1-Vay\u00e1, G., Hermansky, H., Ooster, J., Meyer, B.T.: DNN-based performance measures for predicting error rates in automatic speech recognition and optimizing hearing aid parameters. Speech Commun. 1(106), 44\u201356 (2019)","journal-title":"Speech Commun."},{"key":"740_CR29","doi-asserted-by":"crossref","unstructured":"Ravi Kishore, T., Sai Sidharth, D.: Analysis of Linear and Non-Linear Frequency Modulated Signals Using STFT and Hough Transform, Signal Process. Inf. Technol., 2015.","DOI":"10.1109\/ISSPIT.2015.7394385"},{"key":"740_CR30","doi-asserted-by":"crossref","unstructured":"Ewees, A. A., Mohamed A.E., Essam H.H.: Improved grasshopper optimization algorithm using opposition-based learning. Expert Syst. Appl. 112 (2018): 156\u2013172.","DOI":"10.1016\/j.eswa.2018.06.023"},{"issue":"5","key":"740_CR31","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1109\/TASLP.2017.2687104","volume":"25","author":"X Zhang","year":"2017","unstructured":"Zhang, X., Wang, D.L.: Deep learning based binaural speech separation in reverberant environments. IEEE Trans. Audio Speech Lang. Process. 25(5), 1075\u20131084 (2017)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"740_CR32","doi-asserted-by":"crossref","unstructured":"Gu, R., Lianwu C., Shi-Xiong Z., Jimeng Z., Yong X., Meng Y., Dan S., Yuexian Z., Dong Y.: Neural Spatial Filter: Target Speaker Speech Separation Assisted with Directional Information. In Interspeech, pp. 4290\u20134294. 2019.","DOI":"10.21437\/Interspeech.2019-2266"},{"issue":"8","key":"740_CR33","doi-asserted-by":"publisher","first-page":"e0182580","DOI":"10.1371\/journal.pone.0182580","volume":"12","author":"A Lozano-Diez","year":"2017","unstructured":"Lozano-Diez, A., Zazo, R., Toledano, D.T., Gonzalez-Rodriguez, J.: An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition. PLoS ONE 12(8), e0182580 (2017)","journal-title":"PLoS ONE"},{"issue":"1","key":"740_CR34","first-page":"92","volume":"23","author":"A Narayanan","year":"2015","unstructured":"Narayanan, A., Wang, D.: Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training. IEEE Trans. Audio Speech Lang. Process. 23(1), 92\u2013101 (2015)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"740_CR35","unstructured":"Geiger, J. T., Weninger, F., Gemmeke, J., Wollmer, M., Schuller, B., Rigoll, G.: Memory-enhanced neural networks and NMF for robust ASR, IEEE\/ACM Trans. Audio, Speech, Lang. Process., vol. 22, no. 6, pp. 1037\u20131046, Jun. 2014."},{"key":"740_CR36","doi-asserted-by":"crossref","unstructured":"Weng, S. W. C., Yu, D., Juang, B.-H.: Recurrent deep neural networks for robust speech recognition, in Proc. IEEE Int. Conf. Acoust, Speech, Signal Process., 2014, pp. 5532\u20135536.","DOI":"10.1109\/ICASSP.2014.6854661"},{"key":"740_CR37","unstructured":"Weninger, F., Geiger, J., W\u00f6llmer, M., Schuller, B., Rigoll, G.: The Munich feature enhancement approach to the 2nd CHiME challenge using BLSTM recurrent neural networks, in Proc. 2nd CHiME Workshop Mach. Listening Multisource Environ., 2013, pp. 86\u201390."},{"key":"740_CR38","doi-asserted-by":"crossref","unstructured":"Jin, Y.L., Chen J.T., QianHong L., Yan W.: Multi-Head Self-Attention Based Deep Clustering For Single-Channel Speech Separation. IEEE Access (2020).","DOI":"10.1109\/ACCESS.2020.2997871"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-020-00740-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-020-00740-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-020-00740-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T19:03:58Z","timestamp":1670699038000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-020-00740-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,6]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["740"],"URL":"https:\/\/doi.org\/10.1007\/s00530-020-00740-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,6]]},"assertion":[{"value":"14 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Conflict of interest the authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}