{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T11:01:46Z","timestamp":1740135706894,"version":"3.37.3"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T00:00:00Z","timestamp":1671753600000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s00034-022-02263-5","type":"journal-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T04:20:35Z","timestamp":1671769235000},"page":"3038-3053","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Quartered Spectral Envelope and 1D-CNN-Based Classification of Normally Phonated and Whispered Speech"],"prefix":"10.1007","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3312-2015","authenticated-orcid":false,"given":"S. Johanan","family":"Joysingh","sequence":"first","affiliation":[]},{"given":"P.","family":"Vijayalakshmi","sequence":"additional","affiliation":[]},{"given":"T.","family":"Nagarajan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,23]]},"reference":[{"key":"2263_CR1","doi-asserted-by":"crossref","unstructured":"T. Ashihara, Y. Shinohara, H. Sato, T. Moriya, K. Matsui, T. Fukutomi, Y. Yamaguchi, Y. Aono, Neural whispered speech detection with imbalanced learning, in INTERSPEECH (2019), pp. 3352\u20133356","DOI":"10.21437\/Interspeech.2019-2161"},{"key":"2263_CR2","doi-asserted-by":"crossref","unstructured":"S. Baghel, M. Bhattacharjee, S. Prasanna, P. Guha, Shouted and normal speech classification using 1D CNN, in International Conference on Pattern Recognition and Machine Intelligence (Springer, 2019), pp. 472\u2013480","DOI":"10.1007\/978-3-030-34872-4_52"},{"key":"2263_CR3","volume-title":"The Laryngectomee Guide","author":"I Brook","year":"2013","unstructured":"I. Brook, The Laryngectomee Guide (CreateSpace Publication, Charleston, 2013)"},{"key":"2263_CR4","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1109\/LSP.2019.2961213","volume":"27","author":"M Cotescu","year":"2019","unstructured":"M. Cotescu, T. Drugman, G. Huybrechts, J. Lorenzo-Trueba, A. Moinet, Voice conversion for whispered speech synthesis. IEEE Signal Process. Lett. 27, 186\u2013190 (2019)","journal-title":"IEEE Signal Process. Lett."},{"key":"2263_CR5","first-page":"431","volume":"6","author":"F Cummins","year":"2006","unstructured":"F. Cummins, M. Grimaldi, T. Leonard, J. Simko, The CHAINS corpus: characterizing individual speakers. Proc. SPECOM 6, 431\u2013435 (2006)","journal-title":"Proc. SPECOM"},{"issue":"12","key":"2263_CR6","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1109\/TASLP.2017.2738559","volume":"25","author":"T Grozdi\u0107","year":"2017","unstructured":"T. Grozdi\u0107, S.T. Jovi\u010di\u0107, Whispered speech recognition using deep de-noising autoencoder and inverse filtering. IEEE\/ACM Trans. Audio Speech Lang. Proc. 25(12), 2313\u20132322 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Proc."},{"issue":"2","key":"2263_CR7","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.specom.2003.10.005","volume":"45","author":"T Ito","year":"2005","unstructured":"T. Ito, K. Takeda, F. Itakura, Analysis and recognition of whispered speech. Speech Commun. 45(2), 139\u2013152 (2005)","journal-title":"Speech Commun."},{"key":"2263_CR8","doi-asserted-by":"crossref","unstructured":"Q. Jin, S.C.S. Jou, T. Schultz, Whispering speaker identification, in IEEE International Conference on Multimedia and Expo (IEEE, 2007), pp. 1027\u20131030","DOI":"10.1109\/ICME.2007.4284828"},{"issue":"4","key":"2263_CR9","first-page":"739","volume":"84","author":"ST Jovi\u010di\u0107","year":"1998","unstructured":"S.T. Jovi\u010di\u0107, Formant feature differences between whispered and voiced sustained vowels. Acta Acust. Acust. 84(4), 739\u2013743 (1998)","journal-title":"Acta Acust. Acust."},{"key":"2263_CR10","doi-asserted-by":"crossref","unstructured":"K. Khoria, M.R. Kamble, H.A. Patil, Teager energy cepstral coefficients for classification of normal vs. whisper speech, in 28th European Signal Processing Conference (EUSIPCO) (IEEE, 2021), pp. 1\u20135","DOI":"10.23919\/Eusipco47968.2020.9287634"},{"key":"2263_CR11","unstructured":"B.P. Lim, Computational differences between whispered and non-whispered speech (University of Illinois at Urbana-Champaign, 2011)"},{"issue":"4","key":"2263_CR12","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/PROC.1975.9792","volume":"63","author":"J Makhoul","year":"1975","unstructured":"J. Makhoul, Linear prediction: a tutorial review. Proc. IEEE 63(4), 561\u2013580 (1975)","journal-title":"Proc. IEEE"},{"issue":"17","key":"2263_CR13","first-page":"1","volume":"2004","author":"T Nagarajan","year":"2004","unstructured":"T. Nagarajan, H.A. Murthy, Subband-based group delay segmentation of spontaneous speech into syllable-like units. EURASIP J. Adv. Signal Proc. 2004(17), 1\u201312 (2004)","journal-title":"EURASIP J. Adv. Signal Proc."},{"key":"2263_CR14","doi-asserted-by":"crossref","unstructured":"Z. Qian, K. Xiao, Tagging tone for mandarin pinyin based on sequence labelling. DEStech Transactions on Environment, Energy and Earth Sciences (PEEES) (2020)","DOI":"10.12783\/dteees\/peees2020\/35462"},{"key":"2263_CR15","volume-title":"Discrete-Time Speech Signal Processing: Principles and Practice","author":"TF Quatieri","year":"2002","unstructured":"T.F. Quatieri, Discrete-Time Speech Signal Processing: Principles and Practice (Pearson Education India, Noida, 2002)"},{"key":"2263_CR16","volume-title":"Theory and Applications of Digital Speech Processing","author":"LR Rabiner","year":"2011","unstructured":"L.R. Rabiner, R.W. Schafer, Theory and Applications of Digital Speech Processing (Prentice Hall Inc., Hoboken, 2011)"},{"key":"2263_CR17","doi-asserted-by":"crossref","unstructured":"Z. Raeesy, K. Gillespie, C. Ma, T. Drugman, J. Gu, R. Maas, A. Rastrow, B. Hoffmeister, Lstm-based whisper detection, in IEEE Spoken Language Technology Workshop (SLT) (IEEE, 2018), pp. 139\u2013144","DOI":"10.1109\/SLT.2018.8639614"},{"key":"2263_CR18","doi-asserted-by":"crossref","unstructured":"N.J. Shah, M.A.B. Shaik, P. Periyasamy, H.A. Patil, V. Vij, Exploiting phase-based features for whisper vs. speech classification, in 29th European Signal Processing Conference (EUSIPCO) (IEEE, 2021), pp. 21\u201325","DOI":"10.23919\/EUSIPCO54536.2021.9616337"},{"key":"2263_CR19","doi-asserted-by":"crossref","unstructured":"P. Vijayalakshmi, M.R. Reddy, The analysis on band-limited hypernasal speech using group delay based formant extraction technique, in Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-192"},{"issue":"4","key":"2263_CR20","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1109\/TBME.2006.889191","volume":"54","author":"P Vijayalakshmi","year":"2007","unstructured":"P. Vijayalakshmi, M.R. Reddy, D. O\u2019Shaughnessy, Acoustic analysis and detection of hypernasality using a group delay function. IEEE Trans. Biomed. Eng. 54(4), 621\u2013629 (2007)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2263_CR21","doi-asserted-by":"crossref","unstructured":"S.J. Wenndt, E.J. Cupples, R.M. Floyd, A study on the classification of whispered and normally phonated speech, in Seventh International Conference on Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-214"},{"key":"2263_CR22","unstructured":"J.B. Wilson, J.D. Mosko, A comparative analysis of whispered and normally phonated speech using an LPC-10 vocoder. Technical report. Rome Air Development Center Griffiss AFB NY (1985)"},{"key":"2263_CR23","doi-asserted-by":"crossref","unstructured":"C. Zhang, J.H. Hansen, Analysis and classification of speech mode: whispered through shouted, in Eighth Annual Conference of the International Speech Communication Association (2007)","DOI":"10.21437\/Interspeech.2007-621"},{"key":"2263_CR24","doi-asserted-by":"crossref","unstructured":"C. Zhang, J.H. Hansen, An entropy based feature for whisper-island detection within audio streams, in Ninth Annual Conference of the International Speech Communication Association (2008)","DOI":"10.21437\/Interspeech.2008-622"},{"key":"2263_CR25","doi-asserted-by":"crossref","unstructured":"C. Zhang, J.H. Hansen, Advancements in whisper-island detection within normally phonated audio streams, in Tenth Annual Conference of the International Speech Communication Association (2009)","DOI":"10.21437\/Interspeech.2009-261"},{"issue":"4","key":"2263_CR26","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1109\/TASL.2010.2066967","volume":"19","author":"C Zhang","year":"2010","unstructured":"C. Zhang, J.H. Hansen, Whisper-island detection based on unsupervised segmentation with entropy-based speech feature processing. IEEE Trans. Audio Speech Lang. Process. 19(4), 883\u2013894 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-022-02263-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-022-02263-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-022-02263-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T04:46:48Z","timestamp":1681534008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-022-02263-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,23]]},"references-count":26,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["2263"],"URL":"https:\/\/doi.org\/10.1007\/s00034-022-02263-5","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2022,12,23]]},"assertion":[{"value":"26 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2022","order":4,"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 there are no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}