{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:57:46Z","timestamp":1772301466993,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819755905","type":"print"},{"value":"9789819755912","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5591-2_15","type":"book-chapter","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:02:42Z","timestamp":1723572162000},"page":"174-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TSMGAN-II: Generative Adversarial Network Based on Two-Stage Mask Transformer and Information Interaction for Speech Enhancement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1906-8470","authenticated-orcid":false,"given":"Lianxin","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3335-3398","authenticated-orcid":false,"given":"Yaowen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1197-5906","authenticated-orcid":false,"given":"Haizhou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"issue":"8","key":"15_CR1","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1109\/TASLP.2018.2828980","volume":"26","author":"C Valentini-Botinhao","year":"2018","unstructured":"Valentini-Botinhao, C., Yamagishi, J.: Speech enhancement of noisy and reverberant speech for text-to-speech. IEEE Trans. Audio Speech Lang. Process. 26(8), 1420\u20131433 (2018)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"15_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101869","volume":"99","author":"A Mehrish","year":"2023","unstructured":"Mehrish, A., Majumder, N., Bhardwaj, R., et al.: A review of deep learning techniques for speech processing. Inform. Fus. 99, 101869 (2023)","journal-title":"Inform. Fus."},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wang, Z., Watanabe, S., et al.: Conditional Diffusion Probabilistic Model for Speech Enhancement. In: 47th International Conference on Acoustics, Speech and Signal Processing, pp. 7402\u20137406. IEEE, Singapore, Singapore (2022)","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Shetu, S.S., Chakrabarty, S., Thiergart, O., et al.: Ultra low complexity deep learning based noise suppression. In: 49th International Conference on Acoustics, Speech and Signal Processing, pp. 466\u2013470. IEEE, Seoul, Korea (2024)","DOI":"10.1109\/ICASSP48485.2024.10448353"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Abdulatif, S., Cao, R., Yang, B.: CMGAN: conformer-based metric GAN for speech enhancement. In: 23rd Conference of the International Speech Communication Association, pp. 936\u2013940. IEEE, Incheon, Korea (2022)","DOI":"10.36227\/techrxiv.21187846.v1"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D.: Densely connected neural network with dilated convolutions for real-time speech enhancement in the time domain. In: 45th International Conference on Acoustics, Speech and Signal Processing, pp. 6629\u20136633. IEEE, Barcelona, Spain (2020)","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Wang, K., He, B., Zhu, W.: TSTNN: two-stage transformer based neural network for speech enhancement in the time domain. In: 46th International Conference on Acoustics, Speech and Signal Processing, pp. 7098\u20137102. IEEE, Toronto, Ontario, Canada (2021)","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"15_CR8","unstructured":"Fu, S., Liao, C., Tsao, Y., et al.: MetricGAN: generative adversarial networks based black-box metric scores optimization for speech enhancement. In: 36th International Conference on Machine Learning, pp. 2031\u20132041. PMLR, Long Beach, California, USA (2019)"},{"key":"15_CR9","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.specom.2022.11.004","volume":"146","author":"F Dang","year":"2022","unstructured":"Dang, F., Chen, H., Hu, Q., et al.: First coarse, fine afterward: a lightweight two-stage complex approach for monaural speech enhancement. Speech Commun. 146, 32\u201344 (2022)","journal-title":"Speech Commun."},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M., et al.: Perceptual Evaluation of Speech Quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: 26th International Conference on Acoustics, Speech, and Signal Processing, pp.749\u2013752. IEEE, Salt Lake City, UT, USA (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Hansen, J.H., Pellom, B.L.: An effective quality evaluation protocol for speech enhancement algorithms. In: 5th International Conference on Spoken Language Processing, pp. 2819\u20132822. ISCA, Sydney, Australia (1998)","DOI":"10.21437\/ICSLP.1998-350"},{"issue":"1","key":"15_CR12","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2008","unstructured":"Hu, Y., Loizou, P.C.: Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio Speech Lang. Process. 16(1), 229\u2013238 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kim, E., Seo, H.: SE-conformer: time-domain speech enhancement using conformer. In: 22nd Conference of the International Speech Communication Association, pp. 2736\u20132740. ISCA, Brno, Czechia (2021)","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Yu, G., Li, A., Wang, Y., et al.: Dual-branch attention-in-attention transformer for single-channel speech enhancement. In: 47th International Conference on Acoustics, Speech and Signal Processing, pp. 7847\u20137851. IEEE, Singapore, Singapore (2022)","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Schr\u00f6ter, H., Maier, A., Escalante-B, A.N., et al.: Deepfilternet2: towards real-time speech enhancement on embedded devices for full-band audio. In: 17th International Workshop on Acoustic Signal Enhancement, pp. 1\u20135. IEEE, Bamberg, Germany (2022)","DOI":"10.1109\/IWAENC53105.2022.9914782"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Chao, R., Yu, C., Fu, S., et al.: Perceptual contrast stretching on target feature for speech enhancement. arXiv preprint arXiv:2203.17152 (2022)","DOI":"10.21437\/Interspeech.2022-10478"},{"key":"15_CR17","unstructured":"Shin, W., Lee, B.H., Kim, J.S., et al.: MetricGAN-OKD: multi-metric optimization of MetricGAN via online knowledge distillation for speech enhancement. In: 40th International Conference on Machine Learning, pp. 31521\u201331538. PMLR, Hawaii, USA (2023)"},{"key":"15_CR18","first-page":"1758","volume":"27","author":"W Jiang","year":"2021","unstructured":"Jiang, W., Yu, K.: Speech enhancement with integration of neural homomorphic synthesis and spectral masking. IEEE Trans. Audio Speech Lang. Process. 27, 1758\u20131770 (2021)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"15_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.103008","volume":"156","author":"FE Wahab","year":"2023","unstructured":"Wahab, F.E., Ye, Z., Saleem, N., et al.: Compact deep neural networks for real-time speech enhancement on resource-limited devices. Speech Commun. 156, 103008 (2023)","journal-title":"Speech Commun."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5591-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:05:22Z","timestamp":1723572322000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5591-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755905","9789819755912"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5591-2_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"14 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}