{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:41:02Z","timestamp":1762522862794,"version":"3.37.3"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s10772-023-10045-w","type":"journal-article","created":{"date-parts":[[2023,10,5]],"date-time":"2023-10-05T05:01:46Z","timestamp":1696482106000},"page":"707-720","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Monaural speech separation using WT-Conv-TasNet for hearing aids"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3606-1289","authenticated-orcid":false,"given":"Jharna","family":"Agrawal","sequence":"first","affiliation":[]},{"given":"Manish","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Hitendra","family":"Garg","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,5]]},"reference":[{"key":"10045_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, D., & Bansal, A. (2020). Non-adaptive and adaptive filtering techniques for fingerprint pores extraction. In Advances in data and information sciences (pp. 643\u2013654). Springer.","DOI":"10.1007\/978-981-15-0694-9_59"},{"issue":"20","key":"10045_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-023-14649-x","volume":"82","author":"J Agrawal","year":"2023","unstructured":"Agrawal, J., Gupta, M., & Garg, H. (2023). A review on speech separation in cocktail party environment: Challenges and approaches. Multimedia Tools and Applications, 82(20), 1\u201333.","journal-title":"Multimedia Tools and Applications"},{"key":"10045_CR3","doi-asserted-by":"crossref","unstructured":"Akansu, A. N., & Haddad, R. A. (2001). Wavelet transform. In Multiresolution signal decomposition (2nd ed., pp. 391\u2013442). Academic Press.","DOI":"10.1016\/B978-012047141-6\/50006-9"},{"key":"10045_CR4","doi-asserted-by":"crossref","unstructured":"Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamar\u00eda, J., Albahri, A. S., Al-dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., Duan, Y., Abdullah, A., Farhan, L., Lu, Y., Gupta, A., Albu, F., Abbosh, A., & Gu, Y. (2023). A survey on deep learning tools dealing with data scarcity: Definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1), 46.","DOI":"10.1186\/s40537-023-00727-2"},{"key":"10045_CR5","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.neunet.2021.02.020","volume":"140","author":"BJ Borgstr\u00f6m","year":"2021","unstructured":"Borgstr\u00f6m, B. J., Brandstein, M. S., Ciccarelli, G. A., Quatieri, T. F., & Smalt, C. J. (2021). Speaker separation in realistic noise environments with applications to a cognitively-controlled hearing aid. Neural Networks, 140, 136\u2013147.","journal-title":"Neural Networks"},{"key":"10045_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Luo, Y., & Mesgarani, N. (2017, March). Deep attractor network for single-microphone speaker separation. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 246\u2013250). IEEE.","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"10045_CR7","doi-asserted-by":"crossref","unstructured":"Chiang, H. T., Wu, Y. C., Yu, C., Toda, T., Wang, H. M., Hu, Y. C., & Tsao, Y. (2021). Hasa-net: A non-intrusive hearing-aid speech assessment network. In 2021 IEEE automatic speech recognition and understanding workshop (ASRU) (pp. 907\u2013913). IEEE.","DOI":"10.1109\/ASRU51503.2021.9687972"},{"key":"10045_CR8","doi-asserted-by":"crossref","unstructured":"Deng, C., Zhang, Y., Ma, S., Sha, Y., Song, H., & Li, X. (2020). Conv-TasSAN: Separative adversarial network based on Conv-TasNet. In INTERSPEECH (pp. 2647\u20132651).","DOI":"10.21437\/Interspeech.2020-2371"},{"issue":"6","key":"10045_CR9","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1097\/AUD.0000000000000028","volume":"35","author":"JL Desjardins","year":"2014","unstructured":"Desjardins, J. L., & Doherty, K. A. (2014). The effect of hearing aid noise reduction on listening effort in hearing-impaired adults. Ear and Hearing, 35(6), 600\u2013610.","journal-title":"Ear and Hearing"},{"issue":"2","key":"10045_CR10","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.32604\/csse.2023.025969","volume":"44","author":"JS Esra","year":"2023","unstructured":"Esra, J. S., & Sukhi, Y. (2023). Speech separation methodology for hearing aid. Computer Systems Science and Engineering, 44(2), 1659\u20131678.","journal-title":"Computer Systems Science and Engineering"},{"issue":"5","key":"10045_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439797","volume":"20","author":"X Fan","year":"2021","unstructured":"Fan, X., Yang, B., Chen, W., & Fan, Q. (2021). Deep neural network based noised Asian speech enhancement and its implementation on a hearing aid app. Transactions on Asian and Low-Resource Language Information Processing, 20(5), 1\u201314.","journal-title":"Transactions on Asian and Low-Resource Language Information Processing"},{"key":"10045_CR12","doi-asserted-by":"crossref","unstructured":"Fu, S. W., Tsao, Y., Hwang, H. T., & Wang, H. M. (2018). Quality-Net: An end-to-end non-intrusive speech quality assessment model based on BLSTM. arXiv preprint arXiv:1808.05344.","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"10045_CR13","doi-asserted-by":"publisher","DOI":"10.1177\/23312165211068629","author":"T Green","year":"2022","unstructured":"Green, T., Hilkhuysen, G., Huckvale, M., Rosen, S., Brookes, M., Moore, A., Naylor, P., Lightburn, L., & Xue, W. (2022). Speech recognition with a hearing-aid processing scheme combining beamforming with mask-informed speech enhancement. Trends in Hearing. https:\/\/doi.org\/10.1177\/23312165211068629","journal-title":"Trends in Hearing"},{"key":"10045_CR14","doi-asserted-by":"crossref","unstructured":"Han, C., O\u2019Sullivan, J., Luo, Y., Herrero, J., Mehta, A. D., & Mesgarani, N. (2021). Automatic speech separation enables brain-controlled hearable technologies. In Brain\u2013computer interface research (pp. 95\u2013104). Springer.","DOI":"10.1007\/978-3-030-79287-9_10"},{"key":"10045_CR15","doi-asserted-by":"crossref","unstructured":"Isik, Y., Roux, J. L., Chen, Z., Watanabe, S., & Hershey, J. R. (2016). Single-channel multi-speaker separation using deep clustering. arXiv preprint arXiv:1607.02173.","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"10045_CR16","doi-asserted-by":"crossref","unstructured":"Joder, C., Weninger, F., Eyben, F., Virette, D., & Schuller, B. (2012). Real-time speech separation by semi-supervised nonnegative matrix factorization. In Latent variable analysis and signal separation: 10th international conference, LVA\/ICA 2012, Tel Aviv, Israel, 12\u201315 March 2012. Proceedings 10 (pp. 322-329). Springer.","DOI":"10.1007\/978-3-642-28551-6_40"},{"key":"10045_CR17","doi-asserted-by":"crossref","unstructured":"Kad\u0131o\u011flu, B., Horgan, M., Liu, X., Pons, J., Darcy, D., & Kumar, V. (2020, May). An empirical study of Conv-TasNet. In ICASSP 2020\u20132020 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7264\u20137268). IEEE.","DOI":"10.1109\/ICASSP40776.2020.9054721"},{"issue":"10","key":"10045_CR18","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TASLP.2017.2726762","volume":"25","author":"M Kolb\u00e6k","year":"2017","unstructured":"Kolb\u00e6k, M., Yu, D., Tan, Z. H., & Jensen, J. (2017). Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 25(10), 1901\u20131913.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"10045_CR19","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3390\/app12020832","volume":"12","author":"H Li","year":"2022","unstructured":"Li, H., Chen, K., Wang, L., Liu, J., Wan, B., & Zhou, B. (2022). Sound Source separation mechanisms of different deep networks explained from the perspective of auditory perception. Applied Sciences, 12(2), 832.","journal-title":"Applied Sciences"},{"key":"10045_CR22","volume-title":"End-to-end speech separation with neural networks","author":"Y Luo","year":"2021","unstructured":"Luo, Y. (2021). End-to-end speech separation with neural networks. Columbia University."},{"key":"10045_CR21","doi-asserted-by":"crossref","unstructured":"Luo, Y., Han, C., &Mesgarani, N. (2021, June). Ultra-lightweight speech separation via group communication. In ICASSP 2021\u20132021 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 16\u201320). IEEE.","DOI":"10.1109\/ICASSP39728.2021.9414322"},{"key":"10045_CR20","doi-asserted-by":"crossref","unstructured":"Luo, Y., & Mesgarani, N. (2018, April). Tasnet: Time-domain audio separation network for real-time, single-channel speech separation. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 696\u2013700). IEEE.","DOI":"10.1109\/ICASSP.2018.8462116"},{"issue":"8","key":"10045_CR23","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. (2019). Conv-TasNet: Surpassing ideal time\u2013frequency magnitude masking for speech separation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 27(8), 1256\u20131266.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"5","key":"10045_CR24","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1016\/S0165-1684(02)00140-8","volume":"82","author":"A Munoz","year":"2002","unstructured":"Munoz, A., Ertl\u00e9, R., & Unser, M. (2002). Continuous wavelet transform with arbitrary scales and O(N) complexity. Signal Processing, 82(5), 749\u2013757.","journal-title":"Signal Processing"},{"key":"10045_CR25","doi-asserted-by":"crossref","unstructured":"Nakamura, T., & Saruwatari, H. (2020). Time-domain audio source separation based on Wave-U-Net combined with discrete wavelet transform. In ICASSP 2020\u20132020 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 386\u2013390). IEEE.","DOI":"10.1109\/ICASSP40776.2020.9053934"},{"issue":"2","key":"10045_CR26","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/TASL.2006.876756","volume":"15","author":"TL Nwe","year":"2007","unstructured":"Nwe, T. L., & Li, H. (2007). Exploring vibrato-motivated acoustic features for singer identification. IEEE Transactions on Audio, Speech, and Language Processing, 15(2), 519\u2013530.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10045_CR27","doi-asserted-by":"crossref","unstructured":"O\u2019Grady, P. D., Pearlmutter, B. A., & Rickard, S. T. (2005). Survey of sparse and non\u2010sparse methods in source separation. International Journal of Imaging Systems and Technology, 15(1), 18\u201333.","DOI":"10.1002\/ima.20035"},{"key":"10045_CR28","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015, April). LibriSpeech: An ASR corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5206\u20135210). IEEE.","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"10045_CR29","unstructured":"Pedersen, M. S. (2006). Source separation for hearing aid applications. IMM, Informatikog Matematisk Modelling, DTU."},{"key":"10045_CR30","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1631\/FITEE.1700814","volume":"19","author":"YM Qian","year":"2018","unstructured":"Qian, Y. M., Weng, C., Chang, X. K., Wang, S., & Yu, D. (2018). Past review, current progress, and challenges ahead on the cocktail party problem. Frontiers of Information Technology & Electronic Engineering, 19, 40\u201363.","journal-title":"Frontiers of Information Technology & Electronic Engineering"},{"key":"10045_CR31","first-page":"121","volume":"13","author":"M Sifuzzaman","year":"2009","unstructured":"Sifuzzaman, M., Islam, M. R., & Ali, M. Z. (2009). Application of wavelet transform and its advantages compared to Fourier transform. Journal of Physical Sciences, 13, 121\u2013134.","journal-title":"Journal of Physical Sciences"},{"issue":"4","key":"10045_CR32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11042-021-11775-2","volume":"81","author":"LK Singh","year":"2022","unstructured":"Singh, L. K., Garg, H., & Khanna, M. (2022). Performance evaluation of various deep learning based models for effective glaucoma evaluation using optical coherence tomography images. Multimedia Tools and Applications, 81(4), 1\u201345.","journal-title":"Multimedia Tools and Applications"},{"key":"10045_CR33","doi-asserted-by":"crossref","unstructured":"Subakan, Y. C., & Smaragdis, P. (2018). Generative adversarial source separation. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 26\u201330). IEEE.","DOI":"10.1109\/ICASSP.2018.8461671"},{"key":"10045_CR34","doi-asserted-by":"crossref","unstructured":"Tang, C., Luo, C., Zhao, Z., Xie, W., & Zeng, W. (2021). Joint time-frequency and time domain learning for speech enhancement. In Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence (pp. 3816\u20133822).","DOI":"10.24963\/ijcai.2020\/528"},{"key":"10045_CR35","doi-asserted-by":"crossref","unstructured":"Wang, K., Huang, H., Hu, Y., Huang, Z., & Li, S. (2021). End-to-end speech separation using orthogonal representation in complex and real time-frequency domain. In Proceedings of Interspeech 2021 (pp. 3046\u20133050).","DOI":"10.21437\/Interspeech.2021-504"},{"key":"10045_CR36","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/8677043","author":"L Wang","year":"2021","unstructured":"Wang, L., Zheng, W., Ma, X., & Lin, S. (2021). Denoising speech based on deep learning and wavelet decomposition. Scientific Programming. https:\/\/doi.org\/10.1155\/2021\/8677043","journal-title":"Scientific Programming"},{"key":"10045_CR37","doi-asserted-by":"crossref","unstructured":"Wei, S., Wang, F., & Jiang, D. (2019). Sparse component analysis based on an improved ant K-means clustering algorithm for underdetermined blind source separation. In 2019 IEEE 16th international conference on networking, sensing and control (ICNSC) (pp. 200\u2013205). IEEE.","DOI":"10.1109\/ICNSC.2019.8743171"},{"issue":"3","key":"10045_CR38","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2015","unstructured":"Williamson, D. S., Wang, Y., & Wang, D. (2015). Complex ratio masking for monaural speech separation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(3), 483\u2013492.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10045_CR39","doi-asserted-by":"crossref","unstructured":"Wirsing, K. (2020). Time frequency analysis of wavelet and Fourier transform. In Wavelet theory. InTechOpen.","DOI":"10.5772\/intechopen.94521"},{"key":"10045_CR40","doi-asserted-by":"crossref","unstructured":"Yin, J., Liu, Z., Jin, Y., Peng, D., & Kang, J. (2017). Blind source separation and identification for speech signals. In 2017 International conference on sensing, diagnostics, prognostics, and control (SDPC) (pp. 398\u2013402). IEEE.","DOI":"10.1109\/SDPC.2017.82"},{"issue":"6","key":"10045_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/2196893","volume":"2020","author":"CM Yuan","year":"2020","unstructured":"Yuan, C. M., Sun, X. M., & Zhao, H. (2020). Speech separation using convolutional neural network and attention mechanism. Discrete Dynamics in Nature and Society, 2020(6), 1\u201310.","journal-title":"Discrete Dynamics in Nature and Society"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10045-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-023-10045-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10045-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T14:11:23Z","timestamp":1699625483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-023-10045-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10045"],"URL":"https:\/\/doi.org\/10.1007\/s10772-023-10045-w","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"12 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2023","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 conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}