{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:58:49Z","timestamp":1772301529449,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819785049","type":"print"},{"value":"9789819785056","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/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":[[2025]]},"DOI":"10.1007\/978-981-97-8505-6_26","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:03:53Z","timestamp":1730930633000},"page":"370-378","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MRGAN: LightWeight Monaural Speech Enhancement Using GAN Network"],"prefix":"10.1007","author":[{"given":"Chunyu","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangcun","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanhong","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuike","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Penghao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Cao, R., Abdulatif, S., Yang, B.: CMGAN: conformer-based metric GAN for speech enhancement. In: Proceedings of Interspeech, pp. 936\u2013940 (2022)","DOI":"10.36227\/techrxiv.21187846"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Weninger, F., et al.: Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR. In: International Conference on Latent Variable Analysis and Signal Separation, pp. 91\u201399 (2015)","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Zheng, C., et al.: Interactive speech and noise modeling for speech enhancement. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35(16), pp. 14549\u201314557 (2021)","DOI":"10.1609\/aaai.v35i16.17710"},{"issue":"6","key":"26_CR4","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1097\/AUD.0000000000000028","volume":"35","author":"JL Desjardins","year":"2014","unstructured":"Desjardins, J.L., Doherty, A.K.: The effect of hearing aid noise reduction on listening effort in hearing-impaired adults. Ear Hear. 35(6), 600\u2013610 (2014)","journal-title":"Ear Hear."},{"issue":"10","key":"26_CR5","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang, D., Chen, J.: Supervised speech separation based on deep learning: an overview. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(10), 1702\u20131726 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Pascual, S., Bonafonte, A., Serra, J.: SEGAN: speech enhancement generative adversarial network. In: Proceedings of Interspeech, pp. 3642\u20133646 (2017)","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"26_CR7","unstructured":"Fu, S.-W., Liao, C.-F., Tsao, Y., Lin, S.D.: MetricGAN: generative adversarial networks based black-box metric scores optimization for speech enhancement. In: International Conference on Machine Learning, pp. 2031\u20132041. PMLR (2019)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Rethage, D., Pons, J., Serra, X.: A Wavenet for speech denoising. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5069\u20135073 (2018)","DOI":"10.1109\/ICASSP.2018.8462417"},{"issue":"9","key":"26_CR9","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1109\/TASLP.2018.2821903","volume":"26","author":"SW Fu","year":"2018","unstructured":"Fu, S.W., et al.: End-to-end waveform utterance enhancement for direct evaluation metrics optimization by fully convolutional neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(9), 1570\u20131584 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"26_CR10","doi-asserted-by":"publisher","first-page":"18171","DOI":"10.1038\/s41598-022-22977-5","volume":"12","author":"G Wei","year":"2022","unstructured":"Wei, G., Min, H., Xu, Y., et al.: Lambda-vector modeling temporal and channel interactions for text-independent speaker verification [J]. Sci. Rep. 12(1), 18171 (2022)","journal-title":"Sci. Rep."},{"key":"26_CR11","doi-asserted-by":"publisher","DOI":"10.1201\/b14529","volume-title":"Speech Enhancement: Theory and Practice","author":"PC Loizou","year":"2013","unstructured":"Loizou, P.C.: Speech Enhancement: Theory and Practice, 2nd edn. CRC Press Inc, USA (2013)","edition":"2"},{"issue":"30","key":"26_CR12","doi-asserted-by":"publisher","first-page":"22209","DOI":"10.1007\/s00521-023-08906-1","volume":"35","author":"G Wei","year":"2023","unstructured":"Wei, G., Zhang, Y., Min, H., et al.: End-to-end speaker identification research based on multi-scale SincNet and CGAN [J]. Neural Comput. Appl. 35(30), 22209\u201322222 (2023)","journal-title":"Neural Comput. Appl."},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D.: TCNN: temporal convolutional neural network for real-time speech enhancement in the time domain. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6875\u20136879 (2019)","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Valentini-Botinhao, C., Wang, X., Takaki, S., Yamagishi, J.: Investigating RNN-based speech enhancement methods for noise-robust textto-speech. In: 9th ISCA Speech Synthesis Workshop (SSW), pp. 146\u2013152 (2016)","DOI":"10.21437\/SSW.2016-24"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Lee, D., Choi, D., Choi, J.W.: DeFT-AN RT: real-time multichannel speech enhancement using dense frequency-time attentive network and non-overlapping synthesis window [C]. In: INTERSPEECH. International Speech Communication Association, vol. 2023, pp. 864\u2013868 (2023)","DOI":"10.21437\/Interspeech.2023-2437"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Chen, J., Mao, Q., Liu, D.: Dual-path transformer network: direct context-aware modeling for end-to-end monaural speech separation. In: Proceedings of Interspeech, pp. 2642\u20132646 (2020)","DOI":"10.21437\/Interspeech.2020-2205"},{"issue":"2","key":"26_CR17","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins, H., et al.: Deep learning for audio signal processing. IEEE J. Sel. Top. Signal Process. 13(2), 206\u2013219 (2019)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"26_CR18","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1109\/TASLP.2021.3066303","volume":"29","author":"D Michelsanti","year":"2021","unstructured":"Michelsanti, D., et al.: An overview of deep-Learning-based audio-visual speech enhancement and separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1368\u20131396 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"4","key":"26_CR19","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TASSP.1982.1163920","volume":"30","author":"D Wang","year":"1982","unstructured":"Wang, D., Lim, J.: The unimportance of phase in speech enhancement. IEEE Trans. Acoust. Speech Signal Process. 30(4), 679\u2013681 (1982)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"01","key":"26_CR20","first-page":"1","volume":"7","author":"K Kinoshita","year":"2016","unstructured":"Kinoshita, K., et al.: A summary of the reverb challenge: State-of-theart and remaining challenges in reverberant speech processing research. J. Adv. Signal Process. 7(01), 1\u201319 (2016)","journal-title":"J. Adv. Signal Process."},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Barker, J., Marxer, R., Vincent, E., Watanabe, S.: The third \u2018CHiME\u2019 speech separation and recognition challenge: dataset, task and baselines. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 504\u2013511 (2015)","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Dubey, H., et al.: ICASSP 2022 Deep noise suppression challenge. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2022)","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Yin, D., Luo, C., Xiong, Z., Zeng, W.: PHASEN: a phase-and-harmonics-aware speech enhancement network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34(05), pp. 9458\u20139465 (2020)","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Yu, G., et al.: Dual-branch attention-in-attention transformer for single channel speech enhancement. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7847\u20137851 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"26_CR25","unstructured":"Macartney, C., Weyde, T.: Improved speech enhancement with the Wave-U-Net, arXiv, vol. abs\/1811.11307 (2018)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Wang, K., He, B., Zhu, W.P.: TSTNN: two-stage transformer based neural network for speech enhancement in the time domain. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7098\u20137102 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Defossez, A., Synnaeve, G., Adi, Y.: Real time speech enhancement in the waveform domain. In: Proceedings ofInterspeech, pp. 3291\u20133295 (2020)","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Kim, E., Seo, H.: SE-conformer: time-domain speech enhancement using conformer. In: Proceedings of Interspeech, pp. 2736\u20132740 (2021)","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Abdulatif, S., et al.: AeGAN: time-frequency speech denoising via generative adversarial networks. In: 28th European Signal Processing Conference (EUSIPCO), pp. 451\u2013455 (2020)","DOI":"10.23919\/Eusipco47968.2020.9287606"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Abdulatif, S., et al.: Investigating cross-domain losses for speech enhancement. In: 29th European Signal Processing Conference (EUSIPCO), pp. 411\u2013415 (2021)","DOI":"10.23919\/EUSIPCO54536.2021.9616267"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Sun, L., Yuan, S., Gong, A., et al.: Dual-branch modeling based on state-space model for speech enhancement [J]. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","DOI":"10.1109\/TASLP.2024.3362691"},{"issue":"4","key":"26_CR32","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/0167-6393(90)90010-7","volume":"9","author":"V Zue","year":"1990","unstructured":"Zue, V., Seneff, S., Glass, J.: Speech database development at MIT: TIMIT and beyond [J]. Speech Commun. 9(4), 351\u2013356 (1990)","journal-title":"Speech Commun."},{"issue":"3","key":"26_CR33","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, P.: Complex ratio masking for monaural speech separation. IEEE Trans. Audio Speech Lang. Process. 24(3), 483\u2013492 (2016)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Tan, K., Wang, D.: Complex spectral mapping with a convolutional recurrent network for monaural speech enhancement. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6865\u20136869 (2019)","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"26_CR35","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.1109\/LSP.2021.3116502","volume":"28","author":"ZQ Wang","year":"2021","unstructured":"Wang, Z.Q., Wichern, G., Le Roux, J.: On the compensation between magnitude and phase in speech separation. IEEE Signal Process. Lett. 28, 2018\u20132022 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Li, A., Zheng, C., Zhang, L., Li, X.: Glance and gaze: a collaborative learning framework for single-channel speech enhancement. Appl. Acoust. 187 (2022)","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"26_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"26_CR38","unstructured":"Dang, F., Chen, H., Zhang, P., DPT-FSNet: dual-path transformer based full-band and sub-band fusion network for speech enhancement, arXiv, vol. abs\/2104.13002 (2021)"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Proceedings of Interspeech, pp. 5036\u20135040 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Continuous speech separation with conformer. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5749\u20135753 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"issue":"4","key":"26_CR41","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.: The importance of phase in speech enhancement. Speech Commun. 53(4), 465\u2013494 (2011)","journal-title":"Speech Commun."},{"key":"26_CR42","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.1109\/LSP.2020.3025020","volume":"27","author":"H Phan","year":"2020","unstructured":"Phan, H., et al.: Improving GANs for speech enhancement. IEEE Signal Process. Lett. 27, 1700\u20131704 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Pascual, S., Serra, J., Bonafonte, A.: Towards generalized speech enhancement with generative adversarial networks. In: Proceedings of Interspeech, pp. 1791\u20131795 (2019)","DOI":"10.21437\/Interspeech.2019-2688"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Donahue, C., Li, B., Prabhavalkar, R.: Exploring speech enhancement with generative adversarial networks for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5024\u20135028 (2018)","DOI":"10.1109\/ICASSP.2018.8462581"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8505-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:06:40Z","timestamp":1730930800000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/10.1007\/978-981-97-8505-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":44,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/978-981-97-8505-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2.zoppoz.workers.dev:443\/http\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}