{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T05:25:19Z","timestamp":1732253119965,"version":"3.28.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"8-9","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s11760-024-03263-5","type":"journal-article","created":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T11:01:48Z","timestamp":1718190108000},"page":"5677-5683","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beamforming and lightweight GRU neural network combination model for multi-channel speech enhancement"],"prefix":"10.1007","volume":"18","author":[{"given":"Zhengdong","family":"Cao","sequence":"first","affiliation":[]},{"given":"Dongmei","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"3263_CR1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836","volume-title":"Speech Enhancement: Theory and Practice","author":"PC Loizou","year":"2007","unstructured":"Loizou, P.C.: Speech Enhancement: Theory and Practice. CRC Press, Florida (2007)"},{"key":"3263_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultras.2020.106309","volume":"111","author":"V Perrot","year":"2021","unstructured":"Perrot, V., Polichetti, M., Varray, F., Garcia, D.: So you think you can das? A viewpoint on delay-and-sum beamforming. Ultrasonics 111, 106309 (2021)","journal-title":"Ultrasonics"},{"issue":"8","key":"3263_CR3","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1109\/PROC.1969.7278","volume":"57","author":"J Capon","year":"1969","unstructured":"Capon, J.: High-resolution frequency-wavenumber spectrum analysis. Proc. IEEE 57(8), 1408\u20131418 (1969)","journal-title":"Proc. IEEE"},{"issue":"3","key":"3263_CR4","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/TASSP.1987.1165142","volume":"35","author":"K Buckley","year":"1987","unstructured":"Buckley, K.: Spatial\/spectral filtering with linearly constrained minimum variance beamformers. IEEE Trans. Acoust. Speech Signal Process. 35(3), 249\u2013266 (1987)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"1","key":"3263_CR5","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/TAP.1982.1142739","volume":"30","author":"L Griffiths","year":"1982","unstructured":"Griffiths, L., Jim, C.: An alternative approach to linearly constrained adaptive beamforming. IEEE Trans. Antennas Propag. 30(1), 27\u201334 (1982)","journal-title":"IEEE Trans. Antennas Propag."},{"key":"3263_CR6","doi-asserted-by":"crossref","unstructured":"Dang, F., Chen, H., Zhang, P.: Dpt-fsnet: dual-path transformer based full-band and sub-band fusion network for speech enhancement. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6857\u20136861. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"3263_CR7","doi-asserted-by":"crossref","unstructured":"Pandey, A., Xu, B., Kumar, A., Donley, J., Calamia, P., Wang, D.: Multichannel speech enhancement without beamforming. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6502\u20136506. IEEE, (2022)","DOI":"10.1109\/ICASSP43922.2022.9746704"},{"key":"3263_CR8","doi-asserted-by":"crossref","unstructured":"Fu, S.-W., Tsao, Y., Lu, X., et al: Snr-aware convolutional neural network modeling for speech enhancement. In: Interspeech, pp. 3768\u20133772. (2016)","DOI":"10.21437\/Interspeech.2016-211"},{"issue":"7","key":"3263_CR9","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TASLP.2019.2913512","volume":"27","author":"A Pandey","year":"2019","unstructured":"Pandey, A., Wang, D.: A new framework for cnn-based speech enhancement in the time domain. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(7), 1179\u20131188 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"3263_CR10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1109\/TASLP.2018.2876171","volume":"27","author":"K Tan","year":"2018","unstructured":"Tan, K., Chen, J., Wang, D.: Gated residual networks with dilated convolutions for monaural speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(1), 189\u2013198 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"6","key":"3263_CR11","doi-asserted-by":"publisher","first-page":"4705","DOI":"10.1121\/1.4986931","volume":"141","author":"J Chen","year":"2017","unstructured":"Chen, J., Wang, D.: Long short-term memory for speaker generalization in supervised speech separation. J. Acoust. Soc. Am. 141(6), 4705\u20134714 (2017)","journal-title":"J. Acoust. Soc. Am."},{"key":"3263_CR12","doi-asserted-by":"crossref","unstructured":"Weninger, F., Erdogan, H., Watanabe, S., Vincent, E., Le\u00a0Roux, J., Hershey, J.R., Schuller, B.: Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr. In: Latent Variable Analysis and Signal Separation: 12th International Conference, LVA\/ICA 2015, Liberec, Czech Republic, August 25\u201328, 2015, Proceedings 12, pp. 91\u201399. Springer (2015)","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"3263_CR13","doi-asserted-by":"crossref","unstructured":"Shi, H., Mimura, M., Wang, L., Dang, J., Kawahara, T.: Time-domain speech enhancement assisted by multi-resolution frequency encoder and decoder. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10094718"},{"key":"3263_CR14","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1109\/LSP.2023.3244428","volume":"30","author":"D Lee","year":"2023","unstructured":"Lee, D., Choi, J.-W.: Deft-an: dense frequency-time attentive network for multichannel speech enhancement. IEEE Signal Process. Lett. 30, 155\u2013159 (2023)","journal-title":"IEEE Signal Process. Lett."},{"issue":"4","key":"3263_CR15","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., F\u00e9votte, C.: 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."},{"issue":"12","key":"3263_CR16","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang, Y., Narayanan, A., Wang, D.: On training targets for supervised speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(12), 1849\u20131858 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3263_CR17","doi-asserted-by":"crossref","unstructured":"Huang, P.-S., Kim, M., Hasegawa-Johnson, M., Smaragdis, P.: Deep learning for monaural speech separation. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1562\u20131566. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"3263_CR18","doi-asserted-by":"crossref","unstructured":"Pandey, A., Xu, B., Kumar, A., Donley, J., Calamia, P., Wang, D.: Time-domain ad-hoc array speech enhancement using a triple-path network. arXiv preprint arXiv:2110.11844 (2021)","DOI":"10.21437\/Interspeech.2022-11215"},{"key":"3263_CR19","doi-asserted-by":"crossref","unstructured":"Hu, Y., Liu, Y., Lv, S., Xing, M., Zhang, S., Fu, Y., Wu, J., Zhang, B., Xie, L.: Dccrn: deep complex convolution recurrent network for phase-aware speech enhancement. arXiv preprint arXiv:2008.00264 (2020)","DOI":"10.21437\/Interspeech.2020-2537"},{"issue":"10","key":"3263_CR20","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/TASLP.2014.2337844","volume":"22","author":"L Zhao","year":"2014","unstructured":"Zhao, L., Benesty, J., Chen, J.: Design of robust differential microphone arrays. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(10), 1455\u20131466 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"6","key":"3263_CR21","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1121\/1.1324995","volume":"108","author":"GW Elko","year":"2000","unstructured":"Elko, G.W.: Steerable and variable first-order differential microphone array. Acoust. Soc. Am. J. 108(6), 2699 (2000)","journal-title":"Acoust. Soc. Am. J."},{"key":"3263_CR22","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/LSP.2021.3059533","volume":"28","author":"X Leng","year":"2021","unstructured":"Leng, X., Chen, J., Benesty, J.: A new method to design steerable first-order differential beamformers. IEEE Signal Process. Lett. 28, 563\u2013567 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"3263_CR23","doi-asserted-by":"crossref","unstructured":"Isik, Y., Roux, J.L., Chen, Z., Watanabe, S., Hershey, J.R.: Single-channel multi-speaker separation using deep clustering. arXiv preprint arXiv:1607.02173 (2016)","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"3263_CR24","doi-asserted-by":"crossref","unstructured":"Le\u00a0Roux, J., Wisdom, S., Erdogan, H., Hershey, J.R.: Sdr\u2013half-baked or well done? In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 626\u2013630. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"3263_CR25","unstructured":"Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S.: Getting started with the darpa timit cd-rom: an acoustic phonetic continuous speech database. vol. 107, p. 16. National Institute of Standards and Technology (NIST), Gaithersburgh. (1988)"},{"key":"3263_CR26","doi-asserted-by":"crossref","unstructured":"Scheibler, R., Bezzam, E., Dokmani\u0107, I.: Pyroomacoustics: A python package for audio room simulation and array processing algorithms. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 351\u2013355. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461310"},{"issue":"3","key":"3263_CR27","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., Steeneken, H.J.: Assessment for automatic speech recognition: Ii. noisex-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"3263_CR28","doi-asserted-by":"crossref","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No. 01CH37221), vol. 2, pp. 749\u2013752. IEEE (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"3263_CR29","doi-asserted-by":"crossref","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., Jensen, J.: A short-time objective intelligibility measure for time-frequency weighted noisy speech. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4214\u20134217. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"3263_CR30","doi-asserted-by":"crossref","unstructured":"Luo, Y., Han, C., Mesgarani, N., Ceolini, E., Liu, S.-C.: Fasnet: Low-latency adaptive beamforming for multi-microphone audio processing. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 260\u2013267. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003849"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03263-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03263-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03263-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T17:34:15Z","timestamp":1732210455000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03263-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":30,"journal-issue":{"issue":"8-9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["3263"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03263-5","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"20 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2024","order":4,"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 no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}