{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T19:35:33Z","timestamp":1773516933772,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"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_11","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"130-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing Stutter Detection in\u00a0Speech Using Zero Time Windowing Cepstral Coefficients and\u00a0Phase Information"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6983-3732","authenticated-orcid":false,"given":"Narasinga Vamshi Raghu","family":"Simha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1021-4913","authenticated-orcid":false,"given":"Mirishkar Sai","family":"Ganesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1313-7917","authenticated-orcid":false,"given":"Vuppala Anil","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"11_CR1","unstructured":"Bayerl, S., Wolff von Gudenberg, A., H\u00f6nig, F., Noeth, E., Riedhammer, K.: Ksof: the kassel state of fluency dataset - a therapy centered dataset of stuttering. In: Proceedings of the Language Resources and Evaluation Conference, pp. 1780\u20131787. European Language Resources Association, Marseille, France (Jun 2022)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Bayerl, S.P., Wagner, D., N\u00f6th, E., Riedhammer, K.: Detecting dysfluencies in stuttering therapy using wav2vec 2.0. arXiv preprint arXiv:2204.03417 (2022)","DOI":"10.21437\/Interspeech.2022-10908"},{"key":"11_CR3","doi-asserted-by":"publisher","unstructured":"Bayerl, S.P., Wagner, D., Noeth, E., Riedhammer, K.: Detecting dysfluencies in stuttering therapy using wav2vec 2.0. In: Proceedings of Interspeech 2022, pp. 2868\u20132872 (2022). https:\/\/doi.org\/10.21437\/Interspeech. 2022\u201310908","DOI":"10.21437\/Interspeech"},{"issue":"6","key":"11_CR4","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.specom.2013.02.007","volume":"55","author":"Y Bayya","year":"2013","unstructured":"Bayya, Y., Gowda, D.N.: Spectro-temporal analysis of speech signals using zero-time windowing and group delay function. Speech Commun. 55(6), 782\u2013795 (2013)","journal-title":"Speech Commun."},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Chee, L.S., Ai, O.C., Hariharan, M., Yaacob, S.: Automatic detection of prolongations and repetitions using lpcc. In: 2009 International Conference for Technical Postgraduates (TECHPOS), pp. 1\u20134. IEEE (2009)","DOI":"10.1109\/TECHPOS.2009.5412080"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chee, L.S., Ai, O.C., Hariharan, M., Yaacob, S.: Mfcc based recognition of repetitions and prolongations in stuttered speech using k-nn and lda. In: 2009 IEEE Student Conference on Research and Development (SCOReD), pp. 146\u2013149. IEEE (2009)","DOI":"10.1109\/SCORED.2009.5443210"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Drugman, T., Dubuisson, T., Dutoit, T.: Phase-based information for voice pathology detection. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4612\u20134615. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5947382"},{"key":"11_CR8","unstructured":"Duffy, J.R.: Motor speech disorders e-book: substrates, differential diagnosis, and management. Elsevier Health Sciences (2019)"},{"key":"11_CR9","unstructured":"Guitar, B.: Stuttering: an integrated approach to its nature and treatment. Lippincott Williams & Wilkins (2013)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Howell, P., Davis, S., Bartrip, J.: The university college london archive of stuttered speech (uclass) (2009)","DOI":"10.1044\/1092-4388(2009\/07-0129)"},{"key":"11_CR11","doi-asserted-by":"publisher","unstructured":"Kadiri, S.R., Yegnanarayana, B.: Breathy to tense voice discrimination using zero-time windowing cepstral coefficients (ZTWCCs). In: Proceedings of Interspeech 2018, pp. 232\u2013236 (2018). https:\/\/doi.org\/10.21437\/Interspeech. 2018\u20132498","DOI":"10.21437\/Interspeech"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Kethireddy, R., Kadiri, S.R., Kesiraju, S., Gangashetty, S.V., et al.: Zero-time windowing cepstral coefficients for dialect classification. In: Odyssey, pp. 32\u201338 (2020)","DOI":"10.21437\/Odyssey.2020-5"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Kourkounakis, T., Hajavi, A., Etemad, A.: Detecting multiple speech disfluencies using a deep residual network with bidirectional long short-term memory. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6089\u20136093. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053893"},{"key":"11_CR14","doi-asserted-by":"publisher","first-page":"2986","DOI":"10.1109\/TASLP.2021.3110146","volume":"29","author":"T Kourkounakis","year":"2021","unstructured":"Kourkounakis, T., Hajavi, A., Etemad, A.: Fluentnet: end-to-end detection of stuttered speech disfluencies with deep learning. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2986\u20132999 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Koutsogiannaki, M., Simantiraki, O., Degottex, G., Stylianou, Y.: The importance of phase on voice quality assessment. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-391"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Lea, C., Mitra, V., Joshi, A., Kajarekar, S., Bigham, J.P.: Sep-28k: a dataset for stuttering event detection from podcasts with people who stutter. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6798\u20136802. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413520"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"N\u00f6th, E., et al.: Automatic stuttering recognition using hidden Markov models. In: Proceedings of 6th International Conference on Spoken Language Processing (ICSLP 2000), pp. vol. 4, 65\u201368 (2000). https:\/\/doi.org\/10.21437\/ICSLP.2000-752","DOI":"10.21437\/ICSLP.2000-752"},{"issue":"5","key":"11_CR18","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1109\/PROC.1981.12022","volume":"69","author":"AV Oppenheim","year":"1981","unstructured":"Oppenheim, A.V., Lim, J.S.: The importance of phase in signals. Proc. IEEE 69(5), 529\u2013541 (1981)","journal-title":"Proc. IEEE"},{"issue":"11","key":"11_CR19","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1364\/JOSA.73.001413","volume":"73","author":"AV Oppenheim","year":"1983","unstructured":"Oppenheim, A.V., Lim, J.S., Curtis, S.R.: Signal synthesis and reconstruction from partial fourier-domain information. JOSA 73(11), 1413\u20131420 (1983)","journal-title":"JOSA"},{"issue":"4","key":"11_CR20","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)","journal-title":"Speech Commun."},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Paliwal, K.K., Alsteris, L.: Usefulness of phase spectrum in human speech perception. In: Eighth European Conference on Speech Communication and Technology (2003)","DOI":"10.21437\/Eurospeech.2003-611"},{"key":"11_CR22","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.jfludis.2018.03.002","volume":"56","author":"NB Ratner","year":"2018","unstructured":"Ratner, N.B., MacWhinney, B.: Fluency bank: a new resource for fluency research and practice. J. Fluency Disord. 56, 69\u201380 (2018)","journal-title":"J. Fluency Disord."},{"issue":"5","key":"11_CR23","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.parkreldis.2007.11.006","volume":"14","author":"P Riva-Posse","year":"2008","unstructured":"Riva-Posse, P., Busto-Marolt, L., Schteinschnaider, \u00c1., Martinez-Echenique, L., Cammarota, \u00c1., Merello, M.: Phenomenology of abnormal movements in stuttering. Parkinsonism Related Disorders 14(5), 415\u2013419 (2008)","journal-title":"Parkinsonism Related Disorders"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: Stutternet: stuttering detection using time delay neural network. In: 2021 29th European Signal Processing Conference (EUSIPCO), pp. 426\u2013430. IEEE (2021)","DOI":"10.23919\/EUSIPCO54536.2021.9616063"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: Machine learning for stuttering identification: review, challenges and future directions. Neurocomputing (2022)","DOI":"10.1016\/j.neucom.2022.10.015"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: Robust stuttering detection via multi-task and adversarial learning. In: 2022 30th European Signal Processing Conference (EUSIPCO), pp. 190\u2013194. IEEE (2022)","DOI":"10.23919\/EUSIPCO55093.2022.9909644"},{"key":"11_CR27","unstructured":"Sheikh, S.A., Sahidullah, M., Hirsch, F., Ouni, S.: Introducing ecapa-tdnn and wav2vec2. 0 embeddings to stuttering detection. arXiv preprint arXiv:2204.01564 (2022)"},{"issue":"9","key":"11_CR28","doi-asserted-by":"publisher","first-page":"2483","DOI":"10.1044\/2017_JSLHR-S-16-0343","volume":"60","author":"A Smith","year":"2017","unstructured":"Smith, A., Weber, C.: How stuttering develops: the multifactorial dynamic pathways theory. J. Speech Lang. Hear. Res. 60(9), 2483\u20132505 (2017)","journal-title":"J. Speech Lang. Hear. Res."},{"key":"11_CR29","unstructured":"Ward, D.: Stuttering and cluttering: frameworks for understanding and treatment. Psychology Press (2017)"},{"key":"11_CR30","doi-asserted-by":"publisher","unstructured":"Wi\u015bniewski, M., Kuniszyk-J\u00f3\u017akowiak, W., Smo\u0142ka, E., Suszy\u0144ski, W.: Automatic detection of disorders in a continuous speech with the hidden markov models approach. In: Computer Recognition Systems, vol. 2, pp. 445\u2013453. Springer (2007). https:\/\/doi.org\/10.1007\/978-3-540-75175-5_56","DOI":"10.1007\/978-3-540-75175-5_56"}],"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_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:10:42Z","timestamp":1700597442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_11","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)"}}]}}