{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:49:25Z","timestamp":1742914165539,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031483110"},{"type":"electronic","value":"9783031483127"}],"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\/978-3-031-48312-7_22","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"271-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning Based Speech Quality Assessment Focusing on\u00a0Noise Effects"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3800-7235","authenticated-orcid":false,"given":"Rahul","family":"Jaiswal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5956-5375","authenticated-orcid":false,"given":"Anu","family":"Priya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"22_CR1","unstructured":"ITU-T recommendation P.800: Methods for subjective determination of transmission quality (1996)"},{"key":"22_CR2","unstructured":"ITU-T Coded-Speech Database. Series P, Supplement 23 (1998)"},{"key":"22_CR3","unstructured":"Alim, S.A., Rashid, N.K.A.: Some commonly used speech feature extraction algorithms. In: IntechOpen (2018)"},{"key":"22_CR4","unstructured":"Bruhn, S., Grancharov, V., Kleijn, W.B.: Low-complexity, non-intrusive speech quality assessment. US Patent 8,195,449 (2012)"},{"key":"22_CR5","unstructured":"Brunnstr\u00f6m, K., Beker, S.A., De Moor, K., Dooms, A., Egger, S.: Qualinet white paper on definitions of quality of experience (2013)"},{"issue":"2","key":"22_CR6","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1177\/2515245919898466","volume":"3","author":"M De Rooij","year":"2020","unstructured":"De Rooij, M., Weeda, W.: Cross-validation: a method every psychologist should know. Adv. Methods Pract. Psychol. Sci. 3(2), 248\u2013263 (2020)","journal-title":"Adv. Methods Pract. Psychol. Sci."},{"issue":"1","key":"22_CR7","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10772-012-9162-4","volume":"16","author":"RK Dubey","year":"2013","unstructured":"Dubey, R.K., Kumar, A.: Non-intrusive speech quality assessment using several combinations of auditory features. Int. J. Speech Technol. 16(1), 89\u2013101 (2013)","journal-title":"Int. J. Speech Technol."},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Dubey, R.K., Kumar, A.: Comparison of subjective and objective speech quality assessment for different degradation\/noise conditions. In: IEEE International Conference on Signal Processing and Communication, pp. 261\u2013266 (2015)","DOI":"10.1109\/ICSPCom.2015.7150659"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Falk, T.H., Xu, Q., Chan, W.Y.: Non-intrusive GMM-based speech quality measurement. In: IEEE ICASSP, vol. 1, pp. 125\u2013128 (2005)","DOI":"10.1109\/ICASSP.2005.1415066"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Hines, A., Gillen, E., Harte, N.: Measuring and monitoring speech quality for voice over IP with POLQA, ViSQOL and P.563. In: Interspeech, pp. 438\u2013442 (2015)","DOI":"10.21437\/Interspeech.2015-171"},{"key":"22_CR11","unstructured":"Hirsch, H.G., Pearce, D.: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ASR2000-Automatic Speech Recognition: Challenges for the New Millenium ISCA Tutorial and Research Workshop (ITRW) (2000)"},{"issue":"7\u20138","key":"22_CR12","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"Y Hu","year":"2007","unstructured":"Hu, Y., Loizou, P.C.: Subjective comparison and evaluation of speech enhancement algorithms. Speech Commun. 49(7\u20138), 588\u2013601 (2007)","journal-title":"Speech Commun."},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Jaiswal, R.: Influence of silence and noise filtering on speech quality monitoring. In: 11th IEEE International Conference on Speech Technology and Human-Computer Dialogue (SpeD), pp. 109\u2013113 (2021)","DOI":"10.1109\/SpeD53181.2021.9587364"},{"key":"22_CR14","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-981-16-8129-5_10","volume-title":"Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications","author":"R Jaiswal","year":"2022","unstructured":"Jaiswal, R.: Performance analysis of voice activity detector in presence of non-stationary noise. In: Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications. LNEE, vol. 829, pp. 59\u201365. Springer, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-16-8129-5_10"},{"issue":"1s","key":"22_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3529394","volume":"19","author":"R Jaiswal","year":"2023","unstructured":"Jaiswal, R., Dubey, R.K.: CAQoE: a novel no-reference context-aware speech quality prediction metric. ACM Trans. Multimedia Comput. Commun. Appl. 19(1s), 1\u201323 (2023)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"22_CR16","unstructured":"Jaiswal, R., Hines, A.: The sound of silence: how traditional and deep learning based VAD influences speech quality monitoring. In: 26th Irish Conference on Artificial Intelligence and Cognitive Science (2018)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Jaiswal, R., Romero, D.: Implicit wiener filtering for speech enhancement in non-stationary noise. In: 11th International Conference on Information Science and Technology, pp. 39\u201347. IEEE (2021)","DOI":"10.1109\/ICIST52614.2021.9440639"},{"issue":"4","key":"22_CR18","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/LSP.2006.884129","volume":"14","author":"A Karmakar","year":"2007","unstructured":"Karmakar, A., Kumar, A., Patney, R.: Design of optimal wavelet packet trees based on auditory perception criterion. IEEE Signal Process. Lett. 14(4), 240\u2013243 (2007)","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"22_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1002\/bltj.20228","volume":"12","author":"DS Kim","year":"2007","unstructured":"Kim, D.S., Tarraf, A.: ANIQUE+: a new American National Standard for non-intrusive estimation of narrow-band speech quality. Bell Labs Tech. J. 12(1), 221\u2013236 (2007)","journal-title":"Bell Labs Tech. J."},{"key":"22_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (ICLR) (2015)"},{"issue":"7553","key":"22_CR21","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"issue":"6","key":"22_CR22","doi-asserted-by":"publisher","first-page":"1924","DOI":"10.1109\/TASL.2006.883177","volume":"14","author":"L Malfait","year":"2006","unstructured":"Malfait, L., et al.: The ITU-T standard for single-ended speech quality assessment. IEEE Trans. Audio Speech Lang. Process. 14(6), 1924\u20131934 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"22_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-6704-4","volume-title":"Advances in Principal Component Analysis: Research and Development","author":"GR Naik","year":"2017","unstructured":"Naik, G.R.: Advances in Principal Component Analysis: Research and Development. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-981-10-6704-4"},{"key":"22_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03861-1","volume-title":"Computer Speech: Recognition, Compression, Synthesis","author":"MR Schroeder","year":"2004","unstructured":"Schroeder, M.R.: Computer Speech: Recognition, Compression, Synthesis. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-662-03861-1"},{"key":"22_CR25","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.specom.2021.03.004","volume":"130","author":"MH Soni","year":"2021","unstructured":"Soni, M.H., Patil, H.A.: Non-intrusive quality assessment of noise-suppressed speech using unsupervised deep features. Speech Commun. 130, 27\u201344 (2021)","journal-title":"Speech Commun."},{"issue":"1","key":"22_CR26","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MSP.2008.930649","volume":"26","author":"Z Wang","year":"2009","unstructured":"Wang, Z., Bovik, A.C.: Mean squared error: love it or leave it? a new look at signal fidelity measures. IEEE Signal Process. Maga. 26(1), 98\u2013117 (2009)","journal-title":"IEEE Signal Process. Maga."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48312-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T14:46:26Z","timestamp":1730558786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}