{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:22:27Z","timestamp":1742941347393,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916412"},{"type":"electronic","value":"9789819916429"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-1642-9_10","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:14:57Z","timestamp":1681388097000},"page":"110-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Speech Enhancement Method Combining Two-Branch Communication and\u00a0Spectral Subtraction"],"prefix":"10.1007","author":[{"given":"Ruhan","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajun","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongsheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenghao","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingfu","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Berouti, M, Schwartz, R., Makhoul, J.: Enhancement of speech corrupted by acoustic noise. In: ICASSP IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 4, pp. 208\u2013211 (1979)","DOI":"10.1109\/ICASSP.1979.1170788"},{"issue":"3","key":"10_CR2","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1109\/TASSP.1978.1163086","volume":"26","author":"J Lim","year":"1978","unstructured":"Lim, J., Oppenheim, A.: All-pole modeling of degraded speech. IEEE Trans. Acoust. Speech Signal Process. 26(3), 197\u2013210 (1978)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Ephraim Y.: Statistical-model-based speech enhancement systems. In: Proceedings of the IEEE, vol. 80, no. 10, pp. 1526\u20131555 (1992)","DOI":"10.1109\/5.168664"},{"issue":"1","key":"10_CR4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/0167-6393(91)90027-Q","volume":"10","author":"M Dendrinos","year":"1991","unstructured":"Dendrinos, M., Ba Kamidis, S.G., Carayannis, G.: Speech enhancement from noise: a regenerative approach. Speech Commun. 10(1), 45\u201357 (1991)","journal-title":"Speech Commun."},{"issue":"4","key":"10_CR5","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/89.397090","volume":"3","author":"Y Ephraim","year":"1995","unstructured":"Ephraim, Y., Trees, H.V.: A signal subspace approach for speech enhancement. IEEE Trans. Speech Audio Process. 3(4), 251\u2013266 (1995)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Tamura, S., Waibel, A.: Noise reduction using connectionist models. In: ICASSP, pp. 553\u2013556 (1988)","DOI":"10.1109\/ICASSP.1988.196643"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Parveen, S., Green, P.: Speech enhancement with missing data techniques using recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), pp. 733\u2013736 (2004)","DOI":"10.1109\/ICASSP.2004.1326090"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Lu, X.G., Tsao, Y., Matsuda, S., et al.: Speech enhancement based on deep denoising autoencoder. In: Conference of the International Speech Communication Association, ISCA, pp. 436\u2013440 (2013)","DOI":"10.21437\/Interspeech.2013-130"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Pascual, S., Bonafonte, A., Serr\u00e0, J.: SEGAN: speech enhancement generative adversarial network. Interspeech, 3642\u20133646 (2017)","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Abdulatif, S., Armanious, K., Guirguis, K., et al.: Aegan: time-frequency speech denoising via generative adversarial networks. EUSIPCO, pp. 451\u2013455 (2020)","DOI":"10.23919\/Eusipco47968.2020.9287606"},{"key":"10_CR11","unstructured":"Pan, Q., Gao, T., Zhou, J., et al.: CycleGAN with dual adversarial loss for bone-conducted speech enhancement. CoRR.2021:2111.01430"},{"key":"10_CR12","unstructured":"Yasuda, M., Koizumi, Y., Mazzon, L., et al.: DOA estimation by DNN-based denoising and dereverberation from sound intensity vector. CORR.2019:1910.04415"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Yasuda, M., Koizumi, Y., Saito, S., et al.: Sound event localization based on sound intensity vector refined by DNN-based denoising and source separation. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 651\u2013655 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054462"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Le, X., Chen, H., Chen, K., et al.: DPCRN: dual-path convolution recurrent network for single channel speech enhancement. In: Interspeech, pp. 2811\u20132815 (2021)","DOI":"10.21437\/Interspeech.2021-296"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D.: Dense CNN with self-attention for time-domain speech enhancement. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1270\u20131279 (2021)","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"10_CR16","unstructured":"Jansson, A., Sackfield, A.W., Sung, C.C.: Singing voice separation with deep u-net convolutional networks: US20210256994A1 (2021)"},{"issue":"3","key":"10_CR17","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2016","unstructured":"Williamson, D.S., Wang, Y., Wang, D.L.: Complex ratio masking for monaural speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(3), 483\u2013492 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Yin, D., Luo, C., Xiong, Z., et al.: Phasen: a phase-and-harmonics-aware speech enhancement network. In: Conference on Artificial Intelligence. Association for the Advancement of Artificial Intelligence (AAAI).2020: 9458\u20139465","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Hu, G., Wang, D.L.: Speech segregation based on pitch tracking and amplitude modulation. In: IEEE Workshop on Applications of Signal Processing to Audio & Acoustics, pp. 553\u2013556 (2002)","DOI":"10.1109\/ICASSP.2002.5743777"},{"issue":"11","key":"10_CR20","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1016\/j.specom.2006.09.003","volume":"48","author":"S Srinivasan","year":"2006","unstructured":"Srinivasan, S., Roman, N., Wang, D.L.: Binary and ratio time-frequency masks for robust speech recognition. Speech Commun. 48(11), 1486\u20131501 (2006)","journal-title":"Speech Commun."},{"issue":"12","key":"10_CR21","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.L.: 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."},{"issue":"4","key":"10_CR22","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/j.specom.2010.12.003","volume":"53","author":"K Paliwal","year":"2011","unstructured":"Paliwal, K., W\u00f3jcicki, K., Shannon, B.J.: The importance of phase in speech enhancement. Speech Commun. 53(4), 465\u2013494 (2011)","journal-title":"Speech Commun."},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Erdogan, H., Hershey, J.R., Watanabe, S., et al.: Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 708\u2013712 (2015)","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Selvaraj, P., Eswaran, C.: Ideal ratio mask estimation using supervised DNN approach for target speech signal enhancement. 42(3), 1869\u20131883 (2021)","DOI":"10.3233\/JIFS-211236"},{"key":"10_CR25","unstructured":"Zhou, L., Jiang, W., Xu, J., et al.: Masks fusion with multi-target learning for speech enhancement. Electr. Eng. Syst. Sci. arXiv e-prints (2021)"},{"key":"10_CR26","unstructured":"Zhang, L., Wang, M., Zhang, Z., et al.: Deep interaction between masking and mapping targets for single-channel speech enhancement. CORR.2021:2106.04878"},{"key":"10_CR27","unstructured":"Choi, H.S., Kim, J.H., Huh, J., et al.: Phase-aware speech enhancement with deep complex U-Net In: ICLR. 2019:1903.03107"},{"key":"10_CR28","doi-asserted-by":"publisher","first-page":"101270","DOI":"10.1016\/j.csl.2021.101270","volume":"71","author":"S Routray","year":"2021","unstructured":"Routray, S., Mao, Q.: Phase sensitive masking-based single channel speech enhancement using conditional generative adversarial network. Comput. Speech Lang. 71, 101270 (2021)","journal-title":"Comput. Speech Lang."},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Takahashi, N., Agrawal, P., Goswami, N., et al.: PhaseNet: discretized phase modeling with deep neural networks for audio source separation. In: Interspeech, pp. 2713\u20132717 (2018)","DOI":"10.21437\/Interspeech.2018-1773"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Takamichi, S., Saito, Y., Takamune, N., et al.: Phase reconstruction from amplitude spectrograms based on von-Mises-distribution deep neural network. In: IEEE 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), pp. 286\u2013290 (2018)","DOI":"10.1109\/IWAENC.2018.8521313"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Masuyama, Y., Yatabe, K., Koizumi, Y., et al.: Deep griffin-lim iteration. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 61\u201365 (2019)","DOI":"10.1109\/ICASSP.2019.8682744"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Phan, H., Nguyen, H.L., Chen, O.Y., et al.: Self-attention generative adversarial network for speech enhancement. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7103\u20137107 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414265"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Soni, M.H., Shah, N., Patil, H.A.: Time-frequency masking-based speech enhancement using generative adversarial network. In: ICASSP, pp. 5039\u20135043 (2018)","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"10_CR34","unstructured":"Kim, J.H., Yoo, J., Chun, S., et al.: Multi-domain processing via hybrid denoising networks for speech enhancement. CoRR.2018:1812.08914"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Valentini-Botinhao, C., Wang, X., Takaki, S., et al.: Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech. In: 9th ISCA Speech Synthesis Workshop, SSW, pp. 146\u2013152 (2016)","DOI":"10.21437\/SSW.2016-24"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1642-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T06:49:28Z","timestamp":1729234168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1642-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916412","9789819916429"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1642-9_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"359","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.65","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}