{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:50:36Z","timestamp":1774540236386,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":[[2023,12]]},"DOI":"10.1007\/s10772-023-10073-6","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T10:02:46Z","timestamp":1703844166000},"page":"1117-1129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An optimized convolutional neural network for speech enhancement"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7354-4485","authenticated-orcid":false,"given":"A","family":"Karthik","sequence":"first","affiliation":[]},{"given":"J. L.","family":"Mazher Iqbal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"key":"10073_CR1","doi-asserted-by":"crossref","unstructured":"Abdulbaqi, J., Gu, Y., Chen, S., & Marsic, I. (2020). Residual recurrent neural network for speech enhancement. In ICASSP 2020\u20142020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2020 (pp. 6659\u20136663).","DOI":"10.1109\/ICASSP40776.2020.9053544"},{"key":"10073_CR2","doi-asserted-by":"crossref","unstructured":"Abdulbaqi, J., Gu, Y., & Marsic, I. (2019). RHR-Net: A residual hourglass recurrent neural network for speech enhancement. ArXiv, abs\/1904.07294","DOI":"10.1109\/ICASSP40776.2020.9053544"},{"key":"10073_CR3","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/s10772-021-09830-2","volume":"24","author":"I Bahadur","year":"2021","unstructured":"Bahadur, I., Kumar, S., & Agarwal, P. (2021). Performance measurement of a hybrid speech enhancement technique. International Journal of Speech Technology, 24, 665\u2013677.","journal-title":"International Journal of Speech Technology"},{"key":"10073_CR4","doi-asserted-by":"publisher","first-page":"78421","DOI":"10.1109\/ACCESS.2019.2922370","volume":"7","author":"GS Bhat","year":"2019","unstructured":"Bhat, G. S., Shankar, N., Reddy, C. K. A., & Panahi, I. M. S. (2019). A real-time convolutional neural network based speech enhancement for hearing impaired listeners using smartphone. IEEE Access, 7, 78421\u201378433.","journal-title":"IEEE Access"},{"key":"10073_CR5","first-page":"515","volume":"29","author":"BJ Borgstrom","year":"2020","unstructured":"Borgstrom, B. J., & Brandstein, M. S. (2020). The speech enhancement via attention masking network (SEAMNET): An end-to-end system for joint suppression of noise and reverberation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29, 515\u2013526.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10073_CR6","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/TASLP.2020.3036783","volume":"29","author":"L Chai","year":"2021","unstructured":"Chai, L., Du, J., Liu, Q., & Lee, C. (2021). A cross-entropy-guided measure (CEGM) for assessing speech recognition performance and optimizing DNN-based speech enhancement. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29, 106\u2013117.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"9","key":"10073_CR7","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1109\/TASLP.2018.2821903","volume":"26","author":"S-W Fu","year":"2018","unstructured":"Fu, S.-W., Wang, T.-W., Tsao, Y., Lu, X., & Kawai, H. (2018). End-to-end waveform utterance enhancement for direct evaluation metrics optimization by fully convolutional neural networks. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 26(9), 1570\u20131584.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"21","key":"10073_CR8","doi-asserted-by":"publisher","first-page":"7025","DOI":"10.3390\/s21217025","volume":"21","author":"J Gnanamanickam","year":"2021","unstructured":"Gnanamanickam, J., Natarajan, Y., & SriPreethaa, K. R. (2021). A hybrid speech enhancement algorithm for voice assistance application. Sensors (basel, Switzerland), 21(21), 7025.","journal-title":"Sensors (basel, Switzerland)"},{"key":"10073_CR9","doi-asserted-by":"crossref","unstructured":"Grzywalski, T., & Drgas, S. (2019). Using recurrences in time and frequency within U-Net architecture for speech enhancement. In ICASSP 2019\u20142019 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2019.","DOI":"10.1109\/ICASSP.2019.8682830"},{"key":"10073_CR10","doi-asserted-by":"publisher","first-page":"102","DOI":"10.3390\/computation10060102","volume":"10","author":"M Guti\u00e9rrez-Mu\u00f1oz","year":"2022","unstructured":"Guti\u00e9rrez-Mu\u00f1oz, M., & Coto-Jim\u00e9nez, M. (2022). An experimental study on speech enhancement based on a combination of wavelets and deep learning. Computation, 10, 102. https:\/\/doi.org\/10.3390\/computation10060102","journal-title":"Computation"},{"issue":"2","key":"10073_CR11","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TETCI.2017.2784878","volume":"2","author":"J-C Hou","year":"2018","unstructured":"Hou, J.-C., Wang, S.-S., Lai, Y.-H., Tsao, Y., Chang, H.-W., & Wang, H.-M. (2018). Audio\u2013visual speech enhancement using multimodal deep convolutional neural networks. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(2), 117\u2013128.","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"10073_CR12","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1109\/LSP.2020.3040693","volume":"27","author":"T-A Hsieh","year":"2020","unstructured":"Hsieh, T.-A., Wang, H.-M., Lu, X., & Tsao, Y. (2020). WaveCRN: An efficient convolutional recurrent neural network for end-to-end speech enhancement. IEEE Signal Processing Letters, 27, 2149\u20132153.","journal-title":"IEEE Signal Processing Letters"},{"key":"10073_CR13","doi-asserted-by":"crossref","unstructured":"Jose, W. J. (2020). AMRConvNet: AMR-coded speech enhancement using convolutional neural networks. In 2020 IEEE international conference on systems, man, and cybernetics (SMC), 2020.","DOI":"10.1109\/SMC42975.2020.9283346"},{"key":"10073_CR14","unstructured":"Karthik, A., & Mazher Iqbal, J. L. (2020). Performance estimation based recurrent-convolutional encoder decoder for speech enhancement. International Journal of Advanced Science and Technology, 29(05), 772\u2013777. http:\/\/sersc.org\/journals\/index.php\/IJAST\/article\/view\/9611"},{"key":"10073_CR15","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1007\/s11277-021-08313-6","volume":"119","author":"A Karthik","year":"2021","unstructured":"Karthik, A., & Mazher Iqbal, J. L. (2021). Efficient speech enhancement using recurrent convolution encoder and decoder. Wireless Personal Communication, 119, 1959\u20131973.","journal-title":"Wireless Personal Communication"},{"key":"10073_CR16","doi-asserted-by":"crossref","unstructured":"Kumawat, P., & Manikandan, M. S. (2019). SSQA: Speech signal quality assessment method using spectrogram and 2-D convolutional neural networks for improving efficiency of ASR devices. In 2019 Seventh international conference on digital information processing and communications (ICDIPC), 2019.","DOI":"10.1109\/ICDIPC.2019.8723681"},{"key":"10073_CR17","doi-asserted-by":"publisher","first-page":"78979","DOI":"10.1109\/ACCESS.2020.2989861","volume":"8","author":"T Lan","year":"2020","unstructured":"Lan, T., Lyu, Y., Ye, W., Hui, G., Xu, Z., & Liu, Q. (2020). Combining multi-perspective attention mechanism with convolutional networks for monaural speech enhancement. IEEE Access, 8, 78979\u201378991.","journal-title":"IEEE Access"},{"key":"10073_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107347","volume":"166","author":"A Li","year":"2020","unstructured":"Li, A., Yuan, M., Zheng, C., & Li, X. (2020). Speech enhancement using progressive learning-based convolutional recurrent neural network. Applied Acoustics, 166, 107347.","journal-title":"Applied Acoustics"},{"key":"10073_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2976193","author":"C-L Liu","year":"2020","unstructured":"Liu, C.-L., Fu, S.-W., Li, Y.-J., Huang, J.-W., Wang, H.-M., & Tsao, Y. (2020). Multichannel speech enhancement by raw waveform-mapping using fully convolutional networks. IEEE\/ACM Transactions on Audio, Speech, and Language Processing,. https:\/\/doi.org\/10.1109\/TASLP.2020.2976193","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing,"},{"key":"10073_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-020-00191-3","volume":"2021","author":"J Llombart","year":"2021","unstructured":"Llombart, J., Gonz\u00e1lez, D. R., Miguel, A., Vicente, L., Ortega, A., & Lleida, E. (2021). Progressive loss functions for speech enhancement with deep neural networks. EURASIP Journal on Audio, Speech, and Music Processing, 2021, 1\u201316.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"10073_CR21","doi-asserted-by":"crossref","unstructured":"Mashiana, H. S., Salaria, A., & Kaur, K. (2019). Speech enhancement using residual convolutional neural network. In 2019 International conference on smart systems and inventive technology (ICSSIT), 2019 (pp. 1193\u20131196).","DOI":"10.1109\/ICSSIT46314.2019.8987950"},{"key":"10073_CR22","doi-asserted-by":"crossref","unstructured":"Ouyang, Z., Yu, H., Zhu, W.-P., & Champagne, B. (2019). A fully convolutional neural network for complex spectrogram processing in speech enhancement. In ICASSP 2019\u20142019 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2019.","DOI":"10.1109\/ICASSP.2019.8683423"},{"key":"10073_CR23","doi-asserted-by":"crossref","unstructured":"Pandey, A., & Wang, D. (2019a). TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain. In ICASSP 2019\u20142019 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2019.","DOI":"10.1109\/ICASSP.2019.8683634"},{"issue":"7","key":"10073_CR24","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TASLP.2019.2913512","volume":"27","author":"A Pandey","year":"2019","unstructured":"Pandey, A., & Wang, D. (2019b). A new framework for CNN based speech enhancement in the time domain. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 27(7), 1179\u20131188.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10073_CR25","doi-asserted-by":"crossref","unstructured":"Pandey, A., & Wang, D. (2020). Densely connected neural network with dilated convolutions for real-time speech enhancement in the time domain. In ICASSP 2020\u20142020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2020 (pp. 6629\u20136633).","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"10073_CR26","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/TASLP.2021.3064421","volume":"29","author":"A Pandey","year":"2021","unstructured":"Pandey, A., & Wang, D. (2021). Dense CNN with self-attention for time-domain speech enhancement. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29, 1270\u20131279.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10073_CR27","doi-asserted-by":"crossref","unstructured":"Parthasarathy, S., & Tashev, I. (2018). Convolutional neural network techniques for speech emotion recognition. In 2018 16th International workshop on acoustic signal enhancement (IWAENC), 2018.","DOI":"10.1109\/IWAENC.2018.8521333"},{"key":"10073_CR28","doi-asserted-by":"crossref","unstructured":"Roy, S., & Paliwal, K. K. (2020). Causal convolutional neural network-based Kalman filter for speech enhancement. In 2020 IEEE Asia\u2013Pacific conference on computer science and data engineering (CSDE), 2020 (pp. 1\u20136).","DOI":"10.1109\/CSDE50874.2020.9411565"},{"key":"10073_CR29","doi-asserted-by":"publisher","first-page":"70516","DOI":"10.1109\/ACCESS.2021.3077281","volume":"9","author":"SK Roy","year":"2021","unstructured":"Roy, S. K., Nicolson, A., & Paliwal, K. K. (2021). DeepLPC-MHANet: Multi-head self-attention for augmented Kalman filter-based speech enhancement. IEEE Access, 9, 70516\u201370530.","journal-title":"IEEE Access"},{"key":"10073_CR30","doi-asserted-by":"crossref","unstructured":"Shah, N., Patil, H. A., & Soni, M. H. (2018). Time\u2013frequency mask-based speech enhancement using convolutional generative adversarial network. In 2018 Asia\u2013Pacific Signal and Information Processing Association annual summit and conference (APSIPA ASC), 2018.","DOI":"10.23919\/APSIPA.2018.8659692"},{"key":"10073_CR31","doi-asserted-by":"publisher","unstructured":"Shi, Y., Rong, W., & Zheng, N. (2018). Speech enhancement using convolutional neural network with skip connections. In 2018 11th International symposium on Chinese spoken language processing (ISCSLP), 2018. https:\/\/doi.org\/10.1109\/iscslp.2018.8706591","DOI":"10.1109\/iscslp.2018.8706591"},{"key":"10073_CR32","doi-asserted-by":"crossref","unstructured":"Strake, M., Defraene, B., Fluyt, K., Tirry, W., & Fingscheidt, T. (2020). Fully convolutional recurrent networks for speech enhancement. In ICASSP 2020\u20142020 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2020.","DOI":"10.1109\/ICASSP40776.2020.9054230"},{"issue":"17","key":"10073_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5120\/ijca2018916290","volume":"179","author":"M Tayseer","year":"2018","unstructured":"Tayseer, M., Adeel, A., & Hussain, A. (2018). A survey on techniques for enhancing speech. International Journal of Computer Applications, 179(17), 1\u201314.","journal-title":"International Journal of Computer Applications"},{"key":"10073_CR34","doi-asserted-by":"crossref","unstructured":"Wu, B., Yu, M., Chen, L., Jin, M., Su, D., & Yu, D. (2019). Improving speech enhancement with phonetic embedding features. In 2019 IEEE automatic speech recognition and understanding workshop (ASRU), 2019.","DOI":"10.1109\/ASRU46091.2019.9003987"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10073-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-023-10073-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10073-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T10:17:08Z","timestamp":1704968228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-023-10073-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10073"],"URL":"https:\/\/doi.org\/10.1007\/s10772-023-10073-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]},"assertion":[{"value":"4 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 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":"There is no potential for a conflict of interest with this project.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No credit is due for this creation.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Salutation"}},{"value":"This procedure is carried out without the involvement of people.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Animal and human rights are not being violated in any way.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Rights of humans and animals"}},{"value":"There is no money associated with this effort.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Backing"}}]}}