{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T15:10:36Z","timestamp":1770995436207,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031483080","type":"print"},{"value":"9783031483097","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-48309-7_17","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"200-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Regularization Based Incremental Learning in\u00a0TCNN for\u00a0Robust Speech Enhancement Targeting Effective Human Machine Interaction"],"prefix":"10.1007","author":[{"given":"Kamini","family":"Sabu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mukesh","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nitya","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Shaik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"17_CR1","unstructured":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs, rec. itu-t p. 86 (2001)"},{"key":"17_CR2","doi-asserted-by":"publisher","unstructured":"Barker, J., Marxer, R., Vincent, E., Watanabe, S.: The third \u2018chime\u2019 speech separation and recognition challenge: dataset, task and baselines. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 504\u2013511 (2015). https:\/\/doi.org\/10.1109\/ASRU.2015.7404837","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Biswas, R., Nathwani, K., Abrol, V.: Transfer learning for speech intelligibility improvement in noisy environments. In: Proceedings of the Interspeech 2021, pp. 176\u2013180 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-150","DOI":"10.21437\/Interspeech.2021-150"},{"issue":"6","key":"17_CR4","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1109\/TNN.2006.881710","volume":"17","author":"MC Choy","year":"2006","unstructured":"Choy, M.C., Srinivasan, D., Cheu, R.L.: Neural networks for continuous online learning and control. IEEE Trans. Neural Networks 17(6), 1511\u20131531 (2006). https:\/\/doi.org\/10.1109\/TNN.2006.881710","journal-title":"IEEE Trans. Neural Networks"},{"issue":"5","key":"17_CR5","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/TSA.2003.811544","volume":"11","author":"I Cohen","year":"2003","unstructured":"Cohen, I.: Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging. IEEE Trans. Speech Audio Process. 11(5), 466\u2013475 (2003). https:\/\/doi.org\/10.1109\/TSA.2003.811544","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"6","key":"17_CR6","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"Y Ephraim","year":"1984","unstructured":"Ephraim, Y., Malah, D.: Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 32(6), 1109\u20131121 (1984). https:\/\/doi.org\/10.1109\/TASSP.1984.1164453","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"17_CR7","doi-asserted-by":"publisher","unstructured":"Fu, S.W., Tsao, Y., Lu, X., Kawai, H.: Raw waveform-based speech enhancement by fully convolutional networks. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 006\u2013012 (2017). https:\/\/doi.org\/10.1109\/APSIPA.2017.8281993","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"17_CR8","doi-asserted-by":"publisher","unstructured":"Gnanamanickam, J., Natarajan, Y., Sri Preethaa, K.R.: A hybrid speech enhancement algorithm for voice assistance application. Sensors (Basel) 21(21), 7025 (2021). https:\/\/doi.org\/10.3390\/s21217025","DOI":"10.3390\/s21217025"},{"key":"17_CR9","unstructured":"Goodfellow, I.J., Mirza, M., Da, X., Courville, A.C., Bengio, Y.: An empirical investigation of catastrophic forgeting in gradient-based neural networks. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14\u201316, 2014, Conference Track Proceedings (2014). https:\/\/arxiv.org\/abs\/1312.6211"},{"key":"17_CR10","unstructured":"Jia, X., Li, D.: TFCN: temporal-frequential convolutional network for single-channel speech enhancement. arXiv (2022)"},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Kim, D., Han, H., Shin, H.K., Chung, S.W., Kang, H.G.: Phase continuity: Learning derivatives of phase spectrum for speech enhancement. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6942\u20136946 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746087","DOI":"10.1109\/ICASSP43922.2022.9746087"},{"key":"17_CR12","unstructured":"Kim, J.H., Yoo, J., Chun, S., Kim, A., Ha, J.W.: Multi-domain processing via hybrid denoising networks for speech enhancement. arXiv (2018)"},{"key":"17_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015)., https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"17_CR14","doi-asserted-by":"publisher","unstructured":"Kinoshita, K., Ochiai, T., Delcroix, M., Nakatani, T.: Improving noise robust automatic speech recognition with single-channel time-domain enhancement network. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7009\u20137013 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053266","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"issue":"13","key":"17_CR15","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017). https:\/\/doi.org\/10.1073\/pnas.1611835114","journal-title":"Proc. Natl. Acad. Sci."},{"key":"17_CR16","doi-asserted-by":"publisher","unstructured":"Kishore, V., Tiwari, N., Paramasivam, P.: improved speech enhancement using TCN with multiple encoder-decoder layers. In: Proceedings of the Interspeech, 2020, pp. 4531\u20134535 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-3122","DOI":"10.21437\/Interspeech.2020-3122"},{"key":"17_CR17","unstructured":"Lee, C.C.: Seril (2020). https:\/\/github.com\/ChangLee0903\/SERIL"},{"key":"17_CR18","doi-asserted-by":"publisher","unstructured":"Lee, C.C., Lin, Y.C., Lin, H.T., Wang, H.M., Tsao, Y.: SERIL: noise adaptive speech enhancement using regularization-based incremental learning. In: Proceedings of the Interspeech 2020, pp. 2432\u20132436 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2213","DOI":"10.21437\/Interspeech.2020-2213"},{"issue":"4","key":"17_CR19","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1049\/iet-its.2018.5094","volume":"13","author":"P Lei","year":"2019","unstructured":"Lei, P., Chen, M., Wang, J.: Speech enhancement for in-vehicle voice control systems using wavelet analysis and blind source separation. IET Intel. Transport Syst. 13(4), 693\u2013702 (2019)","journal-title":"IET Intel. Transport Syst."},{"key":"17_CR20","doi-asserted-by":"publisher","first-page":"56798","DOI":"10.1109\/ACCESS.2020.2982212","volume":"8","author":"Y Li","year":"2020","unstructured":"Li, Y., Chen, F., Sun, Z., Ji, J., Jia, W., Wang, Z.: A smart binaural hearing aid architecture leveraging a smartphone app with deep-learning speech enhancement. IEEE Access 8, 56798\u201356810 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2982212","journal-title":"IEEE Access"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Lu, X., Tsao, Y., Matsuda, S., Hori, C.: Speech enhancement based on deep denoising autoencoder. In: Proceedings of the Interspeech 2013, pp. 436\u2013440 (2013). https:\/\/doi.org\/10.21437\/Interspeech.2013-130","DOI":"10.21437\/Interspeech.2013-130"},{"key":"17_CR22","unstructured":"Masana, M., Twardowski, B., van de Weijer, J.: On class orderings for incremental learning (2020)"},{"issue":"2","key":"17_CR23","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0016-0032(96)00063-4","volume":"334","author":"M Men\u00e9ndez","year":"1997","unstructured":"Men\u00e9ndez, M., Pardo, J., Pardo, L., Pardo, M.: The Jensen-Shannon divergence. J. Franklin Inst. 334(2), 307\u2013318 (1997). https:\/\/doi.org\/10.1016\/S0016-0032(96)00063-4","journal-title":"J. Franklin Inst."},{"key":"17_CR24","doi-asserted-by":"publisher","unstructured":"Nair, G.G., Kumar, C.S.: Speech enhancement system for automatic speech recognition in automotive environment. In: 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 01\u201307 (2021). https:\/\/doi.org\/10.1109\/ICCCNT51525.2021.9579986","DOI":"10.1109\/ICCCNT51525.2021.9579986"},{"issue":"4","key":"17_CR25","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). https:\/\/doi.org\/10.1016\/j.specom.2010.12.003","journal-title":"Speech Commun."},{"key":"17_CR26","doi-asserted-by":"publisher","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: 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 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"17_CR27","doi-asserted-by":"publisher","unstructured":"Pandey, A., Wang, D.: A new framework for supervised speech enhancement in the time domain. In: Proceedings of the Interspeech 2018, pp. 1136\u20131140 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1223","DOI":"10.21437\/Interspeech.2018-1223"},{"key":"17_CR28","doi-asserted-by":"publisher","unstructured":"Pandey, A., Wang, D.: TCNN: temporal convolutional neural network for real-time speech enhancement in the time domain. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6875\u20136879 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683634","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Park, S.R., Lee, J.W.: A fully convolutional neural network for speech enhancement. In: Proceedings of the Interspeech 2017, pp. 1993\u20131997 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-1465","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"17_CR30","doi-asserted-by":"publisher","unstructured":"Qian, K., Zhang, Y., Chang, S., Yang, X., Flor\u00eancio, D., Hasegawa-Johnson, M.: Speech enhancement using Bayesian Wavenet. In: Proceedings of the Interspeech 2017, pp. 2013\u20132017 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-1672","DOI":"10.21437\/Interspeech.2017-1672"},{"issue":"2","key":"17_CR31","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.specom.2005.08.005","volume":"48","author":"S Rangachari","year":"2006","unstructured":"Rangachari, S., Loizou, P.C.: A noise-estimation algorithm for highly non-stationary environments. Speech Commun. 48(2), 220\u2013231 (2006). https:\/\/doi.org\/10.1016\/j.specom.2005.08.005","journal-title":"Speech Commun."},{"issue":"6","key":"17_CR32","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1109\/JSTSP.2022.3181782","volume":"16","author":"A Sivaraman","year":"2022","unstructured":"Sivaraman, A., Kim, M.: Efficient personalized speech enhancement through self-supervised learning. IEEE J. Sel. Topics Sig. Process. 16(6), 1342\u20131356 (2022). https:\/\/doi.org\/10.1109\/JSTSP.2022.3181782","journal-title":"IEEE J. Sel. Topics Sig. Process."},{"key":"17_CR33","doi-asserted-by":"publisher","unstructured":"Thiemann, J., Ito, N., Vincent, E.: The diverse environments multi-channel acoustic noise database (DEMAND): a database of multichannel environmental noise recordings. In: Proceedings of Meetings on Acoustics, vol. 19, no. 1, p. 035081 (2013). https:\/\/doi.org\/10.1121\/1.4799597","DOI":"10.1121\/1.4799597"},{"issue":"12","key":"17_CR34","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang, Y., Narayanan, A., Wang, D.: On training targets for supervised speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(12), 1849\u20131858 (2014). https:\/\/doi.org\/10.1109\/TASLP.2014.2352935","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"17_CR35","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. p. 3320\u20133328 (2014)"},{"key":"17_CR36","unstructured":"Zenke, F., Poole, B., Ganguli, S.: Continual learning through synaptic intelligence. In: Proceedings of the 34th International Conference on Machine Learning, pp. 3987\u20133995 (2017)"},{"key":"17_CR37","doi-asserted-by":"publisher","unstructured":"Zezario, R.E., Fuh, C.S., Wang, H.M., Tsao, Y.: Speech enhancement with zero-shot model selection. In: 2021 29th European Signal Processing Conference (EUSIPCO), pp. 491\u2013495 (2021). https:\/\/doi.org\/10.23919\/EUSIPCO54536.2021.9616163","DOI":"10.23919\/EUSIPCO54536.2021.9616163"},{"key":"17_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, G., Yu, L., Wang, C., Wei, J.: Multi-scale temporal frequency convolutional network with axial attention for speech enhancement. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9122\u20139126 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746610","DOI":"10.1109\/ICASSP43922.2022.9746610"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:11:28Z","timestamp":1700597488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"174","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}