{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:23:00Z","timestamp":1783056180798,"version":"3.54.6"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"DOI":"10.1186\/s13634-025-01210-1","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T12:12:38Z","timestamp":1742645558000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["TFDense-GAN: a generative adversarial network for single-channel speech enhancement"],"prefix":"10.1186","volume":"2025","author":[{"given":"Haoxiang","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxiu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaogang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruilong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dengfeng","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,22]]},"reference":[{"key":"1210_CR1","doi-asserted-by":"crossref","unstructured":"D. Rethage, J. Pons, X. Serra, A wavenet for speech denoising, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2018), pp. 5069\u20135073","DOI":"10.1109\/ICASSP.2018.8462417"},{"issue":"7","key":"1210_CR2","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TASLP.2019.2913512","volume":"27","author":"A Pandey","year":"2019","unstructured":"A. Pandey, D. Wang, 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":"8","key":"1210_CR3","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Y. Luo, N. Mesgarani, 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":"1210_CR4","doi-asserted-by":"crossref","unstructured":"Z. Kong, W. Ping, A. Dantrey, B. Catanzaro, Speech denoising in the waveform domain with self-attention, in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2022), pp. 7867\u20137871","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"1210_CR5","doi-asserted-by":"crossref","unstructured":"J. Kim, M. El-Khamy, J. Lee, T-gsa: transformer with gaussian-weighted self-attention for speech enhancement, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2020), pp. 6649\u20136653","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"1210_CR6","doi-asserted-by":"crossref","unstructured":"F. Dang, H. Chen, P. Zhang, 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) (IEEE, 2022), pp. 6857\u20136861","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"issue":"10","key":"1210_CR7","doi-asserted-by":"publisher","first-page":"6395","DOI":"10.1109\/TCYB.2022.3170472","volume":"53","author":"R Ma","year":"2022","unstructured":"R. Ma, S. Li, B. Zhang, L. Fang, Z. Li, Flexible and generalized real photograph denoising exploiting dual meta attention. IEEE Trans. Cybern. 53(10), 6395\u20136407 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"1210_CR8","doi-asserted-by":"crossref","unstructured":"S. Zhao, T.H. Nguyen, B. Ma, Monaural speech enhancement with complex convolutional block attention module and joint time frequency losses, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2021), pp. 6648\u20136652","DOI":"10.1109\/ICASSP39728.2021.9414569"},{"key":"1210_CR9","unstructured":"H. Liu, Q. Kong, Q. Tian, Y. Zhao, D. Wang, C. Huang, Y. Wang, Voicefixer: toward general speech restoration with neural vocoder. arXiv preprint arXiv:2109.13731 (2021)"},{"key":"1210_CR10","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"1210_CR11","doi-asserted-by":"crossref","unstructured":"R. Ma, Y. Zhang, B. Zhang, L. Fang, D. Huang, L. Qi, Learning attention in the frequency domain for flexible real photograph denoising. IEEE Trans. Image Process. (2024)","DOI":"10.1109\/TIP.2024.3404253"},{"key":"1210_CR12","doi-asserted-by":"crossref","unstructured":"J. Chen, Q. Mao, D. Liu, Dual-path transformer network: direct context-aware modeling for end-to-end monaural speech separation, in Interspeech 2020, pp. 2642\u20132646 (2020)","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"1210_CR13","unstructured":"F. Iandola, M. Moskewicz, S. Karayev, R. Girshick, T. Darrell, K. Keutzer, Densenet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)"},{"key":"1210_CR14","doi-asserted-by":"crossref","unstructured":"C. Veaux, J. Yamagishi, S. King, The voice bank corpus: design, collection and data analysis of a large regional accent speech database, in 2013 International Conference Oriental COCOSDA Held Jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA\/CASLRE). IEEE (2013)","DOI":"10.1109\/ICSDA.2013.6709856"},{"issue":"5","key":"1210_CR15","doi-asserted-by":"publisher","first-page":"3591","DOI":"10.1121\/1.4806631","volume":"133","author":"J Thiemann","year":"2013","unstructured":"J. Thiemann, N. Ito, E. Vincent, The diverse environments multi-channel acoustic noise database: a database of multichannel environmental noise recordings. J. Acoust. Soc. Am. 133(5), 3591 (2013)","journal-title":"J. Acoust. Soc. Am."},{"key":"1210_CR16","doi-asserted-by":"crossref","unstructured":"C.K. Reddy, V. Gopal, R. Cutler, E. Beyrami, R. Cheng, H. Dubey, S. Matusevych, R. Aichner, A. Aazami, S. Braun, et al. The interspeech 2020 deep noise suppression challenge: datasets, subjective testing framework, and challenge results. arXiv preprint arXiv:2005.13981 (2020)","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"1210_CR17","unstructured":"D.P. Kingma, J. Ba, Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"7","key":"1210_CR18","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"C.H. Taal, R.C. Hendriks, R. Heusdens, J. Jensen, An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19(7), 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1210_CR19","doi-asserted-by":"crossref","unstructured":"A.W. Rix, J.G. Beerends, M.P. Hollier, A.P. Hekstra, Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 749\u2013752 (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"1210_CR20","doi-asserted-by":"publisher","unstructured":"J.L. Roux, S. Wisdom, H. Erdogan, J.R. Hershey, Sdr\u2013Half-baked or well done?, in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, pp. 626\u2013630 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683855","DOI":"10.1109\/ICASSP.2019.8683855"},{"issue":"1","key":"1210_CR21","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2007","unstructured":"Y. Hu, P.C. Loizou, Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio Speech Lang. Process. 16(1), 229\u2013238 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1210_CR22","doi-asserted-by":"crossref","unstructured":"A. Defossez, G. Synnaeve, Y. Adi, Real time speech enhancement in the waveform domain. arXiv preprint arXiv:2006.12847 (2020)","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"1210_CR23","doi-asserted-by":"crossref","unstructured":"K. Wang, B. He, W.-P. Zhu, Tstnn: Two-stage transformer based neural network for speech enhancement in the time domain, in ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2021), pp. 7098\u20137102","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"1210_CR24","doi-asserted-by":"crossref","unstructured":"E. Kim, H. Seo, Se-conformer: time-domain speech enhancement using conformer, in Interspeech (2021), pp. 2736\u20132740","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"1210_CR25","doi-asserted-by":"crossref","unstructured":"Y. Hu, Y. Liu, S. Lv, M. Xing, S. Zhang, Y. Fu, J. Wu, B. Zhang, L. Xie, Dccrn: deep complex convolution recurrent network for phase-aware speech enhancement. arXiv preprint arXiv:2008.00264 (2020)","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"1210_CR26","doi-asserted-by":"crossref","unstructured":"G. Yu, A. Li, C. Zheng, Y. Guo, Y. Wang, H. Wang, Dual-branch attention-in-attention transformer for single-channel speech enhancement, in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2022), pp. 7847\u20137851","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"1210_CR27","doi-asserted-by":"crossref","unstructured":"L. Wang, W. Wei, Y. Chen, Y. Hu, D2net: a denoising and dereverberation network based on two-branch encoder and dual-path transformer, in 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (IEEE, 2022), pp. 1649\u20131654","DOI":"10.23919\/APSIPAASC55919.2022.9979863"},{"key":"1210_CR28","doi-asserted-by":"crossref","unstructured":"D. Yin, C. Luo, Z. Xiong, W. Zeng, Phasen: a phase-and-harmonics-aware speech enhancement network, in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34 (2020), pp. 9458\u20139465","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"1210_CR29","doi-asserted-by":"crossref","unstructured":"D. Yin, Z. Zhao, C. Tang, Z. Xiong, C. Luo, Tridentse: guiding speech enhancement with 32 global tokens. arXiv preprint arXiv:2210.12995 (2022)","DOI":"10.21437\/Interspeech.2023-565"},{"key":"1210_CR30","unstructured":"Y.-X. Lu, Y. Ai, Z.-H. Ling, Explicit estimation of magnitude and phase spectra in parallel for high-quality speech enhancement. arXiv preprint arXiv:2308.08926 (2023)"},{"key":"1210_CR31","doi-asserted-by":"crossref","unstructured":"R. Cao, S. Abdulatif, B. Yang, Cmgan: conformer-based metric gan for speech enhancement. arXiv preprint arXiv:2203.15149 (2022)","DOI":"10.36227\/techrxiv.21187846.v2"},{"key":"1210_CR32","unstructured":"S.-W. Fu, C. Yu, T.-A. Hsieh, P. Plantinga, M. Ravanelli, X. Lu, Y. Tsao, Metricgan+: an improved version of metricgan for speech enhancement. arXiv preprint arXiv:2104.03538 (2021)"},{"key":"1210_CR33","doi-asserted-by":"crossref","unstructured":"N.L. Westhausen, B.T. Meyer, Dual-signal transformation lstm network for real-time noise suppression. arXiv preprint arXiv:2005.07551 (2020)","DOI":"10.21437\/Interspeech.2020-2631"},{"key":"1210_CR34","doi-asserted-by":"crossref","unstructured":"U. Isik, R. Giri, N. Phansalkar, J.-M. Valin, K. Helwani, A. Krishnaswamy, Poconet: better speech enhancement with frequency-positional embeddings, semi-supervised conversational data, and biased loss. arXiv preprint arXiv:2008.04470 (2020)","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"1210_CR35","doi-asserted-by":"crossref","unstructured":"X. Hao, X. Su, R. Horaud, X. Li, Fullsubnet: a full-band and sub-band fusion model for real-time single-channel speech enhancement, in ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2021), pp. 6633\u20136637","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"1210_CR36","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1109\/TASLP.2021.3079813","volume":"29","author":"A Li","year":"2021","unstructured":"A. Li, W. Liu, C. Zheng, C. Fan, X. Li, Two heads are better than one: a two-stage complex spectral mapping approach for monaural speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1829\u20131843 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"1210_CR37","doi-asserted-by":"crossref","unstructured":"S. Zhao, B. Ma, K.N. Watcharasupat, W.-S. Gan, Frcrn: boosting feature representation using frequency recurrence for monaural speech enhancement, in ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2022), pp. 9281\u20139285","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"1210_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499","volume":"187","author":"A Li","year":"2022","unstructured":"A. Li, C. Zheng, L. Zhang, X. Li, Glance and gaze: a collaborative learning framework for single-channel speech enhancement. Appl. Acoust. 187, 108499 (2022)","journal-title":"Appl. Acoust."},{"key":"1210_CR39","doi-asserted-by":"crossref","unstructured":"A. Li, S. You, G. Yu, C. Zheng, X. Li, Taylor, can you hear me now? A taylor-unfolding framework for monaural speech enhancement. arXiv preprint arXiv:2205.00206 (2022)","DOI":"10.24963\/ijcai.2022\/582"},{"key":"1210_CR40","doi-asserted-by":"crossref","unstructured":"L. Liu, H. Guan, J. Ma, W. Dai, G. Wang, S. Ding, A mask free neural network for monaural speech enhancement. arXiv preprint arXiv:2306.04286 (2023)","DOI":"10.21437\/Interspeech.2023-339"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-025-01210-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13634-025-01210-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-025-01210-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T12:12:55Z","timestamp":1742645575000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-025-01210-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,22]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1210"],"URL":"https:\/\/doi.org\/10.1186\/s13634-025-01210-1","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,22]]},"assertion":[{"value":"19 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2025","order":3,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10"}}