{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:12:59Z","timestamp":1750219979896,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T00:00:00Z","timestamp":1666310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,21]]},"DOI":"10.1145\/3573428.3573693","type":"proceedings-article","created":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T10:43:09Z","timestamp":1678876989000},"page":"1504-1510","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Noise Processing Methods of Speech Recognition in Noisy Environment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8174-1120","authenticated-orcid":false,"given":"Zebin","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Information Engineering, Beijing Institute of Graphic Communication, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0765-511X","authenticated-orcid":false,"given":"Nan","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing International Studies University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9186-4415","authenticated-orcid":false,"given":"Shulin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Beijing Institute of Graphic Communication, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.19358\/j.issn.2096-5133.2019.08.008"},{"key":"e_1_3_2_1_2_1","first-page":"9117","article-title":"Explore relative and context information with transformer for joint acoustic echo cancellation and speech enhancement [C]\/\/ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"2022","unstructured":"Sun X, Cao C, Li Q, Explore relative and context information with transformer for joint acoustic echo cancellation and speech enhancement [C]\/\/ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022: 9117-9121.","journal-title":"IEEE"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.27251\/d.cnki.gnjdc.2021.000390"},{"key":"e_1_3_2_1_4_1","volume-title":"Optimization on VTS Feature Compensation for Speech Recognition [D]","author":"LI H J","year":"2016","unstructured":"LI H J. Optimization on VTS Feature Compensation for Speech Recognition [D]. Southeast University, 2016."},{"volume-title":"Adaptive very deep convolutional residual network for noise robust speech recognition [J]","year":"2018","key":"e_1_3_2_1_5_1","unstructured":"Tan T, Qian Y, Hu H, Adaptive very deep convolutional residual network for noise robust speech recognition [J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 2018, 26(8): 1393-1405."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.27123\/d.cnki.ghlju.2021.000266"},{"issue":"2","key":"e_1_3_2_1_7_1","first-page":"7","article-title":"A Review of Speech Enhancement Technology Research [J]","volume":"37","author":"CAO L J","year":"2020","unstructured":"CAO L J. A Review of Speech Enhancement Technology Research [J]. Journal of the Hebei Academy of Sciences, 2020, 37(2):7.","journal-title":"Journal of the Hebei Academy of Sciences"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"volume-title":"IEEE International Conference on ICASSP '79","year":"1979","key":"e_1_3_2_1_9_1","unstructured":"Berouti M , Schwartz R , Makhoul J . Enhancement of speech corrupted by acoustic noise [C]\/\/ Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '79. IEEE, 1979."},{"issue":"03","key":"e_1_3_2_1_10_1","first-page":"67","article-title":"Improved Wiener Filter Speech Enhancement Based on Multi-window Spectral Estimation [J]","volume":"34","author":"ZHANG Q","year":"2017","unstructured":"ZHANG Q, WU J. Improved Wiener Filter Speech Enhancement Based on Multi-window Spectral Estimation [J]. Computer Applications and Software, 2017, 34(03): 67-70+118.","journal-title":"Computer Applications and Software"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.27398\/d.cnki.gxalu.2020.000854"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.27426\/d.cnki.gxtdu.2021.000098"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.27272\/d.cnki.gshdu.2020.000743"},{"issue":"10","key":"e_1_3_2_1_14_1","first-page":"2","article-title":"Research on Speech Recognition Algorithm in Noise Environment [J]","volume":"15","author":"ZHAO X","year":"2019","unstructured":"ZHAO X. Research on Speech Recognition Algorithm in Noise Environment [J]. Computer Knowledge and Technology: Academic Edition, 2019, 15(10):2.","journal-title":"Computer Knowledge and Technology: Academic Edition"},{"key":"e_1_3_2_1_15_1","volume-title":"State-space microphone array nonlinear acoustic echo cancellation using multi-microphone near-end speech covariance [J]","author":"H.","year":"2019","unstructured":"Park J, Chang J H. State-space microphone array nonlinear acoustic echo cancellation using multi-microphone near-end speech covariance [J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 2019, 27(10): 1520-1534."},{"key":"e_1_3_2_1_16_1","first-page":"6919","article-title":"Context-aware deep acoustic echo cancellation [C]\/\/ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"2020","author":"CAD-AEC","unstructured":"Fazel A, El-Khamy M, Lee J. CAD-AEC: Context-aware deep acoustic echo cancellation [C]\/\/ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020: 6919-6923.","journal-title":"IEEE"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.16157\/j.issn.0258-7998.212404"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14004\/j.cnki.ckt.2022.0955"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.27049\/d.cnki.ggldc.2021.000036"},{"key":"e_1_3_2_1_20_1","volume-title":"Research of Speaker Verification on Feature Compensation [D]","author":"HUA C.","year":"2014","unstructured":"HUA C. Research of Speaker Verification on Feature Compensation [D]. University of Science and Technology of China, 2014."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1914702"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.27256\/d.cnki.gnbou.2019.000626"},{"key":"e_1_3_2_1_23_1","volume-title":"IEEE","author":"J.","year":"2009","unstructured":"Boril H, Hansen J. Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment [C]\/\/ IEEE International Conference on Acoustics. IEEE, 2009."},{"volume-title":"Proceedings. (ICASSP '04). IEEE International Conference on. IEEE","year":"2004","key":"e_1_3_2_1_24_1","unstructured":"Yoshizawa S, Hayasaka N, Wada N, Cepstral gain normalization for noise robust speech recognition [C]\/\/ Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on. IEEE, 2004."},{"key":"e_1_3_2_1_25_1","volume-title":"Research on Robust Speech Recognition in Noise Environment [D]","author":"WANG L.","year":"2016","unstructured":"WANG L. Research on Robust Speech Recognition in Noise Environment [D]. Harbin Institute of Technology, 2016."},{"key":"e_1_3_2_1_26_1","volume-title":"Channel Compensation for Speaker Recognition [D]","author":"LI Y J","year":"2009","unstructured":"LI Y J. Channel Compensation for Speaker Recognition [D]. University of Science and Technology of China, 2009."},{"key":"e_1_3_2_1_27_1","volume-title":"Noise-Robust Methods for Automatic Speech Recognition [D]","author":"DU J.","year":"2009","unstructured":"DU J. Noise-Robust Methods for Automatic Speech Recognition [D]. University of Science and Technology of China, 2009."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.27276\/d.cnki.gsdgc.2021.000332"},{"key":"e_1_3_2_1_29_1","volume-title":"Survey on Speech Recognition [J]. Computer Systems & Applications","author":"MA H","year":"2022","unstructured":"MA H, TANG R B, ZHANG Y, Survey on Speech Recognition [J]. Computer Systems & Applications, 2022, 31(1):1-10."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.27675\/d.cnki.gcydx.2018.000582"},{"key":"e_1_3_2_1_31_1","volume-title":"IEEE","author":"J.","year":"2014","unstructured":"Xue F, Zhang Y, Glass J. Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition [C]\/\/ IEEE International Conference on Acoustics. IEEE, 2014."},{"volume-title":"Learning spectral mapping for speech dereverberation and denoising [J]","year":"2015","key":"e_1_3_2_1_32_1","unstructured":"Han K, Wang Y, Wang D L, Learning spectral mapping for speech dereverberation and denoising [J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 2015, 23(6): 982-992."},{"key":"e_1_3_2_1_33_1","first-page":"1700","article-title":"A late reverberation power spectral density aware approach to speech dereverberation based on deep neural networks [C]\/\/2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","volume":"2019","unstructured":"Qi Y, Yang F, Yang J. A late reverberation power spectral density aware approach to speech dereverberation based on deep neural networks [C]\/\/2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2019: 1700-1703.","journal-title":"IEEE"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.15888\/j.cnki.csa.006542"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.16543\/j.2095-641x.electric.power.ict.2021.09.012"},{"issue":"13","key":"e_1_3_2_1_36_1","first-page":"49","article-title":"Research on noise robustness of speech recognition based on deep auto-encoder neural network [J]","volume":"53","author":"HUANG L X","year":"2017","unstructured":"HUANG L X, WANG Y N, ZHANG X Y, Research on noise robustness of speech recognition based on deep auto-encoder neural network [J]. Computer Engineering and Applications, 2017, 53(13): 49-54.","journal-title":"Computer Engineering and Applications"},{"key":"e_1_3_2_1_37_1","first-page":"245","article-title":"Deep learning based speech recognition method [J]","volume":"08","author":"BI X W","year":"2019","unstructured":"BI X W. Deep learning based speech recognition method [J]. Electronic Technology & Software Engineering, 2019, (08): 245.","journal-title":"Electronic Technology & Software Engineering"},{"key":"e_1_3_2_1_38_1","first-page":"78","volume-title":"Speaker and Language Characterization (SPLC)","year":"2008","unstructured":"Dehak N, Dehak R, Kenny P, Comparison between factor analysis and GMM support vector machines for speaker verification [J]. Speaker and Language Characterization (SPLC), 2008, 47(12):78-82."},{"key":"e_1_3_2_1_39_1","volume-title":"IEEE","author":"F.","year":"2015","unstructured":"Wang D, Zheng T F. Transfer Learning for Speech and Language Processing [C]\/\/ 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA). IEEE, 2015."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.26969\/d.cnki.gbydu.2021.000376"},{"issue":"02","key":"e_1_3_2_1_41_1","first-page":"156","article-title":"Vocal effort related robust speech recognition based on adaptation method. [J]","volume":"52","author":"CHAO H","year":"2016","unstructured":"CHAO H, SONG C, XUE X, Vocal effort related robust speech recognition based on adaptation method. [J]. Computer Engineering and Applications, 2016, 52(02): 156-160+204.","journal-title":"Computer Engineering and Applications"},{"key":"e_1_3_2_1_42_1","volume-title":"Research on Distant Speech Recognition with Joint Enhancement and Adaptive Technology [D]","author":"LOU Y D","year":"2019","unstructured":"LOU Y D. Research on Distant Speech Recognition with Joint Enhancement and Adaptive Technology [D]. Taiyuan University of Technology, 2019."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.27517\/d.cnki.gzkju.2020.000435"},{"issue":"03","key":"e_1_3_2_1_44_1","first-page":"618","article-title":"Robust Speaker-Recognition Algorithm with Environmental Self-Learning Mechanism [J]","volume":"53","author":"ZHANG J","year":"2020","unstructured":"ZHANG J, YU Y B. Robust Speaker-Recognition Algorithm with Environmental Self-Learning Mechanism [J]. Communications Technology, 2020, 53(03): 618-624.","journal-title":"Communications Technology"},{"issue":"12","key":"e_1_3_2_1_45_1","first-page":"20","article-title":"Survey of Application of Deep Learning in Image Recognition [J]","volume":"55","author":"ZHENG Y P","year":"2019","unstructured":"ZHENG Y P, LI G Y, LI Y. Survey of Application of Deep Learning in Image Recognition [J]. Computer Engineering and Applications, 2019, 55(12): 20-36.","journal-title":"Computer Engineering and Applications"},{"issue":"01","key":"e_1_3_2_1_46_1","first-page":"11","article-title":"Survey on deep belief network model and its applications [J]","volume":"54","author":"LIU F Y","year":"2018","unstructured":"LIU F Y, WANG S H, ZHANG Y D. Survey on deep belief network model and its applications [J]. Computer Engineering and Applications, 2018, 54(01): 11-18+47.","journal-title":"Computer Engineering and Applications"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"e_1_3_2_1_48_1","volume-title":"Dual-path Self-Attention RNN for Real-Time Speech Enhancement [J\/OL]. arXiv preprint arXiv: 201012713","author":"D.","year":"2020","unstructured":"Pandey A, Wang D. Dual-path Self-Attention RNN for Real-Time Speech Enhancement [J\/OL]. arXiv preprint arXiv: 201012713, 2020, https:\/\/arxiv.org\/pdf\/2010.12713.pdf."},{"volume-title":"IEEE","year":"2014","key":"e_1_3_2_1_49_1","unstructured":"Han K, Wang Y, Wang D L . Learning spectral mapping for speech dereverberation [C]\/\/ IEEE International Conference on Acoustics. IEEE, 2014."},{"key":"e_1_3_2_1_50_1","volume-title":"A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement [C]\/\/ INTERSPEECH","author":"D.","year":"2018","unstructured":"Tan K, Wang D. A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement [C]\/\/ INTERSPEECH, 2018. 3229-3233."},{"key":"e_1_3_2_1_51_1","volume-title":"Speech and Signal Processing (ICASSP). IEEE","author":"M\u2217","year":"2018","unstructured":"Karjol P, M\u2217 Ajay Kumar, Ghosh P K. SPEECH ENHANCEMENT USING MULTIPLE DEEP NEURAL NETWORKS [C]\/\/ ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018."},{"key":"e_1_3_2_1_52_1","first-page":"6649","volume-title":"Speech and Signal Processing (ICASSP)","year":"2020","unstructured":"Kim J, El-Khamy M, Lee J. T-gsa: Transformer with gaussian-weighted self-attention for speech enhancement [C]\/\/ IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. IEEE: 6649-6653."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.27461\/d.cnki.gzjdx.2021.002363"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.27224\/d.cnki.gnmdu.2021.001749"},{"key":"e_1_3_2_1_55_1","volume-title":"Deep learning based binaural speech separation in reverberant environments [J]","author":"D.","year":"2017","unstructured":"Zhang X, Wang D. Deep learning based binaural speech separation in reverberant environments [J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 2017, 25(5): 1075-1084."},{"key":"e_1_3_2_1_56_1","first-page":"07","article-title":"Survey of Deep Learning Based Multimodal Emotion Recognition [J\/OL]","volume":"1","author":"ZHAO X M","year":"2022","unstructured":"ZHAO X M, YANG Y J, ZHANG S Q. Survey of Deep Learning Based Multimodal Emotion Recognition [J\/OL]. Journal of Frontiers of Computer Science and Technology: 1-29, 2022, 07, 03. http:\/\/kns.cnki.net\/kcms\/detail\/11.5602.TP.20220303.1827.006.html","journal-title":"Journal of Frontiers of Computer Science and Technology"}],"event":{"name":"EITCE 2022: 2022 6th International Conference on Electronic Information Technology and Computer Engineering","acronym":"EITCE 2022","location":"Xiamen China"},"container-title":["Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573428.3573693","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573428.3573693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:24Z","timestamp":1750182564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573428.3573693"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,21]]},"references-count":56,"alternative-id":["10.1145\/3573428.3573693","10.1145\/3573428"],"URL":"https:\/\/doi.org\/10.1145\/3573428.3573693","relation":{},"subject":[],"published":{"date-parts":[[2022,10,21]]},"assertion":[{"value":"2023-03-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}