{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:23:16Z","timestamp":1783056196983,"version":"3.54.6"},"reference-count":34,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T00:00:00Z","timestamp":1674691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Most previous speech enhancement methods only predict amplitude features, but more and more studies have proved that phase information is crucial for speech quality. Recently, there have also been some methods to choose complex features, but complex masks are difficult to estimate. Removing noise while maintaining good speech quality at low signal-to-noise ratios is still a problem. This study proposes a dual-path network structure for speech enhancement that can model complex spectra and amplitudes simultaneously, and introduces an attention-aware feature fusion module to fuse the two features to facilitate overall spectrum recovery. In addition, we improve a transformer-based feature extraction module that can efficiently extract local and global features. The proposed network achieves better performance than the baseline models in experiments on the Voice Bank + DEMAND dataset. We also conducted ablation experiments to verify the effectiveness of the dual-path structure, the improved transformer, and the fusion module, and investigated the effect of the input-mask multiplication strategy on the results.<\/jats:p>","DOI":"10.3390\/e25020228","type":"journal-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T01:58:59Z","timestamp":1674784739000},"page":"228","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Improved Transformer-Based Dual-Path Network with Amplitude and Complex Domain Feature Fusion for Speech Enhancement"],"prefix":"10.3390","volume":"25","author":[{"given":"Moujia","family":"Ye","sequence":"first","affiliation":[{"name":"Information Engineering Department, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongjie","family":"Wan","sequence":"additional","affiliation":[{"name":"Information Engineering Department, Beijing University of Chemical Technology, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1293","DOI":"10.1109\/TASLP.2020.2986896","article-title":"Robust speaker recognition based on single-channel and multi-channel speech enhancement","volume":"28","author":"Taherian","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TSA.2003.814458","article-title":"A generalized subspace approach for enhancing speech corrupted by colored noise","volume":"11","author":"Hu","year":"2003","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_3","first-page":"113","article-title":"Suppression of acoustic noise in speech using spectral subtraction","volume":"27","author":"Boll","year":"1979","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1109\/18.382009","article-title":"De-noising by soft-thresholding","volume":"41","author":"Donoho","year":"1995","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Luo, Y., Chen, Z., and Yoshioka, T. (2020, January 4\u20138). Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation. Proceedings of the ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Fu, S.-W., Tsao, Y., and Lu, X. (2016, January 8\u201312). SNR-aware convolutional neural network modeling for speech enhancement. Proceedings of the INTERSPEECH 2016, San Francisco, CA, USA.","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref_7","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zarar, S., Tashev, I., and Lee, C.-H. (2018, January 15\u201320). Convolutional-Recurrent Neural Networks for Speech Enhancement. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.","DOI":"10.1109\/ICASSP.2018.8462155"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Braun, S., Gamper, H., Reddy, C.K.A., and Tashev, I. (2021, January 6\u201311). Towards Efficient Models for Real-Time Deep Noise Suppression. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9413580"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Le, X., Chen, H., Chen, K., and Lu, J. (2021). DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement. arXiv.","DOI":"10.21437\/Interspeech.2021-296"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1109\/TASLP.2021.3138716","article-title":"Neural cascade architecture with triple-domain loss for speech enhancement","volume":"30","author":"Wang","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"16591","DOI":"10.1109\/ACCESS.2021.3053408","article-title":"INet: Convolutional Networks for Biomedical Image Segmentation","volume":"9","author":"Weng","year":"2021","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhao, S., Nguyen, T.H., and Ma, B. (2021, January 6\u201311). Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9414569"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, G., Wang, C., Yu, L., and Wei, J. (2022, January 23\u201327). Multi-Scale Temporal Frequency Convolutional Network with Axial Attention for Multi-Channel Speech Enhancement. Proceedings of the ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Marina Bay Sands, Singapore.","DOI":"10.1109\/ICASSP43922.2022.9746902"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Subakan, C., Ravanelli, M., Cornell, S., Bronzi, M., and Zhong, J. (2021, January 6\u201311). Attention Is All You Need in Speech Separation. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Fu, Y., Liu, Y., Li, J., Luo, D., Lv, S., Jv, Y., and Xie, L. (2022, January 23\u201327). Uformer: A Unet Based Dilated Complex & Real Dual-Path Conformer Network for Simultaneous Speech Enhancement and Dereverberation. Proceedings of the ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Marina Bay Sands, Singapore.","DOI":"10.1109\/ICASSP43922.2022.9746020"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, K., He, B., and Zhu, W.P. (2021, January 6\u201311). TSTNN: Two-Stage Transformer Based Neural Network for Speech Enhancement in the Time Domain. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"Xu","year":"2015","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Erdogan, H., Hershey, J.R., Watanabe, S., and Roux, J.L. (2015, January 19\u201324). Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia.","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1109\/TASLP.2020.2986877","article-title":"Multi-Level Single-Channel Speech Enhancement Using a Unified Framework for Estimating Magnitude and Phase Spectra","volume":"28","author":"Lavanya","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Li, A., Liu, W., Luo, X., Zheng, C., and Li, X. (2021, January 6\u201311). ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9414062"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex ratio masking for monaural speech separation","volume":"24","author":"Williamson","year":"2016","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_23","first-page":"1","article-title":"Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry, and Fusion","volume":"17","author":"Wang","year":"2021","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3134","DOI":"10.1109\/TASLP.2022.3209943","article-title":"Fusing Bone-Conduction and Air-Conduction Sensors for Complex-Domain Speech Enhancement","volume":"30","author":"Wang","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","article-title":"Conv-TasNet: Surpassing ideal time\u2013frequency magnitude masking for speech separation","volume":"27","author":"Luo","year":"2019","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, J., Mao, Q., and Liu, D. (2020). Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation. arXiv.","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., and Barnard, K. (2021, January 14). Attentional Feature Fusion. Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1829","DOI":"10.1109\/TASLP.2021.3079813","article-title":"Two heads are better than one: A two-stage complex spectral mapping approach for monaural speech enhancement","volume":"29","author":"Li","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Huszar, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., and Wang, Z. (2016, January 27\u201330). Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Pandey, A., and Wang, D. (2020, January 4\u20138). Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in The Time Domain. Proceedings of the ICASSP 2020\u20142020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Valentini-Botinhao, C., Wang, X., Takaki, S., and Yamagishi, J. (2016, January 8\u201312). Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System using Deep Recurrent Neural Networks. Proceedings of the INTERSPEECH 2016, San Francisco, CA, USA.","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref_33","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., and Hekstra, A.P. (2001, January 7\u201311). Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. Proceedings of the 2001 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Salt Lake City, UT, USA."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TASL.2007.911054","article-title":"Evaluation of objective quality measures for speech enhancement","volume":"16","author":"Hu","year":"2008","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/2\/228\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:16:06Z","timestamp":1760120166000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/2\/228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,26]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["e25020228"],"URL":"https:\/\/doi.org\/10.3390\/e25020228","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,26]]}}}