{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T12:20:52Z","timestamp":1763900452547,"version":"3.45.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"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":["SIViP"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11760-025-04913-y","type":"journal-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T18:28:26Z","timestamp":1761416906000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-branch time-frequency perception network for acoustic echo cancellation"],"prefix":"10.1007","volume":"19","author":[{"given":"Zhaodi","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Jian-Hong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ji-Long","family":"He","sequence":"additional","affiliation":[]},{"given":"Xueting","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"key":"4913_CR1","doi-asserted-by":"crossref","unstructured":"Falconer, D.D.: Adaptive filter theory and applications. In: Analysis and Optimization of Systems: Proceedings of the Fourth International Conference on Analysis and Optimization of Systems Versailles, December 16\u201319, 1980, pp. 161\u2013188 (2005). Springer","DOI":"10.1007\/BFb0004040"},{"key":"4913_CR2","first-page":"807","volume-title":"Academic Press Library in Signal Processing","author":"G Enzner","year":"2014","unstructured":"Enzner, G., Buchner, H., Favrot, A., Kuech, F.: Acoustic echo control. In: Cohen, I., Krishnapuram, R., Lewicki, M.S., Mitra, S.K., Sayed, A.H. (eds.) Academic Press Library in Signal Processing, pp. 807\u2013877. Elsevier, Amsterdam (2014)"},{"issue":"1","key":"4913_CR3","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/TE.2003.822632","volume":"47","author":"E Soria","year":"2004","unstructured":"Soria, E., Calpe, J., Chambers, J., Mart\u00ednez, M., Camps, G., Guerrero, J.D.M.: A novel approach to introducing adaptive filters based on the lms algorithm and its variants. IEEE Trans. Educ. 47(1), 127\u2013133 (2004)","journal-title":"IEEE Trans. Educ."},{"issue":"1","key":"4913_CR4","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1186\/s13634-015-0283-1","volume":"2015","author":"C Paleologu","year":"2015","unstructured":"Paleologu, C., Ciochin\u0103, S., Benesty, J., Grant, S.L.: An overview on optimized nlms algorithms for acoustic echo cancellation. EURASIP Journal on Advances in Signal Processing 2015(1), 97 (2015)","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"4913_CR5","doi-asserted-by":"crossref","unstructured":"Parisae, V., Bhavanam, S.N., Devi, M.V.: Progressive learning framework for speech enhancement using multi-scale convolution and s-tcn. In: 2024 8th International Conference on Inventive Systems and Control (ICISC), pp. 83\u201389 (2024)","DOI":"10.1109\/ICISC62624.2024.00021"},{"key":"4913_CR6","doi-asserted-by":"crossref","unstructured":"Jannu, C., Vanambathina, S.D.: An attention based densely connected u-net with convolutional gru for speech enhancement. In: 2023 3rd International Conference on Artificial Intelligence and Signal Processing (AISP), pp. 1\u20135 (2023)","DOI":"10.1109\/AISP57993.2023.10134933"},{"issue":"1","key":"4913_CR7","first-page":"1195","volume":"45","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: Dct based densely connected convolutional gru for real-time speech enhancement. Journal of Intelligent & Fuzzy Systems 45(1), 1195\u20131208 (2023)","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"7","key":"4913_CR8","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/s11760-025-04158-9","volume":"19","author":"L Luo","year":"2025","unstructured":"Luo, L., Fan, X., Wang, M., Liu, Z., Zhang, Y.: Two-stage deep complex gated convolution attention network for multi-channel noise suppression. SIViP 19(7), 512 (2025)","journal-title":"SIViP"},{"key":"4913_CR9","unstructured":"Ma, L., Huang, H., Zhao, P., Su, T.: Acoustic echo cancellation by combining adaptive digital filter and recurrent neural network. arXiv preprint (2020)"},{"key":"4913_CR10","doi-asserted-by":"crossref","unstructured":"Yang, D., Jiang, F., Wu, W., Fang, X., Cao, M.: Low-complexity acoustic echo cancellation with neural kalman filtering. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023). IEEE","DOI":"10.1109\/ICASSP49357.2023.10096597"},{"issue":"01","key":"4913_CR11","doi-asserted-by":"publisher","first-page":"2550001","DOI":"10.1142\/S0219467825500019","volume":"25","author":"C Jannu","year":"2025","unstructured":"Jannu, C., Vanambathina, S.D.: An overview of speech enhancement based on deep learning techniques. International Journal of Image and Graphics 25(01), 2550001 (2025)","journal-title":"International Journal of Image and Graphics"},{"key":"4913_CR12","doi-asserted-by":"crossref","unstructured":"Fazel, A., El-Khamy, M., Lee, J.: Deep multitask acoustic echo cancellation. In: Interspeech, pp. 4250\u20134254 (2019)","DOI":"10.21437\/Interspeech.2019-2908"},{"key":"4913_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xu, X., Tu, W.: Improving acoustic echo cancellation by exploring speech and echo affinity with multi-head attention. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 401\u2013405 (2024). IEEE","DOI":"10.1109\/ICASSP48485.2024.10446389"},{"key":"4913_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, S., Kong, Y., Lv, S., Hu, Y., Xie, L.: Ft-lstm based complex network for joint acoustic echo cancellation and speech enhancement. arXiv preprint arXiv:2106.07577 (2021)","DOI":"10.21437\/Interspeech.2021-1359"},{"key":"4913_CR15","doi-asserted-by":"crossref","unstructured":"Han, C., Xu, X., Tu, W., Yang, Y., Liu, Y.: Exploring the interactions between target positive and negative information for acoustic echo cancellation. arXiv preprint arXiv:2307.13888 (2023)","DOI":"10.21437\/Interspeech.2023-1364"},{"issue":"5","key":"4913_CR16","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1007\/s11227-025-07200-2","volume":"81","author":"Y Huang","year":"2025","unstructured":"Huang, Y., Qin, W., Li, Z., Zhang, Q.: Time-frequency dual-domain attention for acoustic echo cancellation. J. Supercomput. 81(5), 739 (2025)","journal-title":"J. Supercomput."},{"issue":"12","key":"4913_CR17","doi-asserted-by":"publisher","first-page":"7467","DOI":"10.1007\/s00034-023-02455-7","volume":"42","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: Multi-stage progressive learning-based speech enhancement using time-frequency attentive squeezed temporal convolutional networks. Circuits Systems Signal Process. 42(12), 7467\u20137493 (2023)","journal-title":"Circuits Systems Signal Process."},{"key":"4913_CR18","doi-asserted-by":"crossref","unstructured":"Vanambathina, S.D., Nandyala, S., Jannu, C., Sirisha\u00a0Devi, J., Yechuri, S., Parisae, V.: Speech enhancement using u-net-based progressive learning with squeeze-tcn. In: International Conference on Advances in Distributed Computing and Machine Learning, pp. 419\u2013432 (2024). Springer","DOI":"10.1007\/978-981-97-3523-5_31"},{"key":"4913_CR19","unstructured":"Gu, R., Wu, J., Zhang, S.-X., Chen, L., Xu, Y., Yu, M., Su, D., Zou, Y., Yu, D.: End-to-end multi-channel speech separation. arXiv preprint arXiv:1905.06286 (2019)"},{"issue":"4","key":"4913_CR20","first-page":"10907","volume":"46","author":"V Parisae","year":"2024","unstructured":"Parisae, V., Nagakishore Bhavanam, S.: Multi scale encoder-decoder network with time frequency attention and s-tcn for single channel speech enhancement. Journal of Intelligent & Fuzzy Systems 46(4), 10907\u201310907 (2024)","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"4913_CR21","doi-asserted-by":"crossref","unstructured":"Parisae, V., Nagakishore\u00a0Bhavanam, S.: Stacked u-net with time\u2013frequency attention and deep connection net for single channel speech enhancement. International Journal of Image and Graphics, 2550067 (2024)","DOI":"10.1142\/S0219467825500676"},{"key":"4913_CR22","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. arXiv preprint arXiv:2007.13975 (2020)","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"4913_CR23","doi-asserted-by":"crossref","unstructured":"Shi, H., Mimura, M., Wang, L., Dang, J., Kawahara, T.: Time-domain speech enhancement assisted by multi-resolution frequency encoder and decoder. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023). IEEE","DOI":"10.1109\/ICASSP49357.2023.10094718"},{"key":"4913_CR24","doi-asserted-by":"crossref","unstructured":"Jannu, C., Vanambathina, S.D.: Convolutional transformer based local and global feature learning for speech enhancement. International Journal of Advanced Computer Science and Applications 14(1) (2023)","DOI":"10.14569\/IJACSA.2023.0140181"},{"key":"4913_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, S., Liu, C., Liu, G.: Facial expression recognition based on visual transformers and local attention features network. In: 2022 7th International Conference on Computer and Communication Systems (ICCCS), pp. 228\u2013231 (2022). IEEE","DOI":"10.1109\/ICCCS55155.2022.9846106"},{"key":"4913_CR26","doi-asserted-by":"crossref","unstructured":"Cutler, R., Saabas, A., P\u00e4rnamaa, T., Loide, M., Sootla, S., Purin, M., Gamper, H., Braun, S., S\u00f8rensen, K., Aichner, R., et al.: Interspeech 2021 acoustic echo cancellation challenge. In: Interspeech, pp. 4748\u20134752 (2021)","DOI":"10.21437\/Interspeech.2021-1870"},{"key":"4913_CR27","doi-asserted-by":"crossref","unstructured":"Sridhar, K., Cutler, R., Saabas, A., Parnamaa, T., Loide, M., Gamper, H., Braun, S., Aichner, R., Srinivasan, S.: Icassp 2021 acoustic echo cancellation challenge: Datasets, testing framework, and results. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 151\u2013155 (2021). IEEE","DOI":"10.1109\/ICASSP39728.2021.9413457"},{"key":"4913_CR28","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1109\/OJSP.2024.3376289","volume":"5","author":"R Cutler","year":"2024","unstructured":"Cutler, R., Saabas, A., P\u00e4rnamaa, T., Purin, M., Indenbom, E., Ristea, N.-C., Gu\u017evin, J., Gamper, H., Braun, S., Aichner, R.: Icassp 2023 acoustic echo cancellation challenge. IEEE Open Journal of Signal Processing 5, 675\u2013685 (2024)","journal-title":"IEEE Open Journal of Signal Processing"},{"issue":"8","key":"4913_CR29","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Luo, Y., Mesgarani, N.: Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM transactions on audio, speech, and language processing 27(8), 1256\u20131266 (2019)","journal-title":"IEEE\/ACM transactions on audio, speech, and language processing"},{"key":"4913_CR30","doi-asserted-by":"crossref","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No. 01CH37221), vol. 2, pp. 749\u2013752 (2001). IEEE","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"4913_CR31","doi-asserted-by":"crossref","unstructured":"Taal, C.H., Hendriks, R.C., Heusdens, R., Jensen, J.: A short-time objective intelligibility measure for time-frequency weighted noisy speech. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4214\u20134217 (2010). IEEE","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"4913_CR32","doi-asserted-by":"crossref","unstructured":"Purin, M., Sootla, S., Sponza, M., Saabas, A., Cutler, R.: Aecmos: A speech quality assessment metric for echo impairment. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 901\u2013905 (2022). IEEE","DOI":"10.1109\/ICASSP43922.2022.9747836"},{"key":"4913_CR33","doi-asserted-by":"crossref","unstructured":"Xia, Y., Braun, S., Reddy, C.K., Dubey, H., Cutler, R., Tashev, I.: Weighted speech distortion losses for neural-network-based real-time speech enhancement. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 871\u2013875 (2020). IEEE","DOI":"10.1109\/ICASSP40776.2020.9054254"},{"key":"4913_CR34","doi-asserted-by":"crossref","unstructured":"Westhausen, N.L., Meyer, B.T.: Acoustic echo cancellation with the dual-signal transformation lstm network. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7138\u20137142 (2021). IEEE","DOI":"10.1109\/ICASSP39728.2021.9413510"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04913-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04913-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04913-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T12:13:53Z","timestamp":1763900033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04913-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"references-count":34,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4913"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04913-y","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,10,25]]},"assertion":[{"value":"17 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2025","order":4,"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 known competing financial interests or personal relationships.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"1320"}}