{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:39:13Z","timestamp":1776879553396,"version":"3.51.2"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,8,17]],"date-time":"2017-08-17T00:00:00Z","timestamp":1502928000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s10772-017-9445-x","type":"journal-article","created":{"date-parts":[[2017,8,17]],"date-time":"2017-08-17T11:38:46Z","timestamp":1502969926000},"page":"787-797","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Significance of incorporating excitation source parameters for improved emotion recognition from speech and electroglottographic signals"],"prefix":"10.1007","volume":"20","author":[{"given":"D.","family":"Pravena","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8172-0370","authenticated-orcid":false,"given":"D.","family":"Govind","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,8,17]]},"reference":[{"key":"9445_CR1","doi-asserted-by":"crossref","unstructured":"Adiga, N. & Prasanna, S. R. M. (2013). Significance of instants of significant excitation for source modeling. In Proceedings of INTERSPEECH.","DOI":"10.21437\/Interspeech.2013-29"},{"key":"9445_CR2","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"ME Ayadi","year":"2011","unstructured":"Ayadi, M. E., Kamel, M. S., & Karray, F. (2011). Survey on speech emotion recognition: Features, classification schemes and databases. Pattern Recognition, 44, 572\u2013587.","journal-title":"Pattern Recognition"},{"key":"9445_CR3","doi-asserted-by":"crossref","first-page":"4547","DOI":"10.1121\/1.2909562","volume":"123","author":"M Bulut","year":"2008","unstructured":"Bulut, M., & Narayanan, S. (2008). On the robustness of overall f0 only modifications to the perception of emotions in speech. The Journal of the Acoustical Society of America, 123, 4547\u20134558.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9445_CR4","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlemeier, W., & Weiss, B. (2005). A database of German emotional speech. In Proceedings of INTERSPEECH (pp. 1517\u20131520).","DOI":"10.21437\/Interspeech.2005-446"},{"key":"9445_CR5","unstructured":"Cabral, J. P., & Oliveira, L. C. (2006). Emo voice: A system to generate emotions in speech. in Proceedings of the INTERSPEECH (pp. 1798\u20131801)."},{"key":"9445_CR6","unstructured":"Cahn, J. E. (1989). Generation of affect in synthesized speech. In Proceedings of the American voice I\/O society (pp. 1\u201319)."},{"key":"9445_CR7","unstructured":"Cerezo, E. & Baldassarri, S. (2007). Interactive agents for multimodal emotional user interaction. In In Proceedings of the international conference on interfaces and hman computer interaction."},{"key":"9445_CR8","unstructured":"Creed, C., & Beal, R. (2005). Using emotion simulation to influence user attitudes and behaviors. In Proceedings of workshop on role of emotion in HCI."},{"issue":"4","key":"9445_CR9","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1250\/ast.26.317","volume":"26","author":"D Erickson","year":"2005","unstructured":"Erickson, D. (2005). Expressive speech: Production, perception and application to speech synthesis. Acoustical Science and Technology, 26(4), 317\u2013325.","journal-title":"Acoustical Science and Technology"},{"key":"9445_CR10","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1080\/03637753909374863","volume":"6","author":"G Fairbanks","year":"1939","unstructured":"Fairbanks, G., & Hoaglin, L. W. (1939). An experimental study of pitch characteristics of voice during the expression of emotion. Speech Monographs, 6, 87\u2013104.","journal-title":"Speech Monographs"},{"key":"9445_CR11","volume-title":"Acoustic theory of speech production","author":"G Fant","year":"1960","unstructured":"Fant, G. (1960). Acoustic theory of speech production. s-Gravenhage: Moutan & Co."},{"issue":"7","key":"9445_CR12","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1007\/s00034-015-0159-5","volume":"35","author":"D Govind","year":"2016","unstructured":"Govind, D., & Joy, T. T. (2016). Improving the flexibility of dynamic prosody modification using instants of significant excitation. International Journal of Circuits Systems and Signal Processing, 35(7), 2518\u20132543.","journal-title":"International Journal of Circuits Systems and Signal Processing"},{"key":"9445_CR15","doi-asserted-by":"crossref","unstructured":"Govind D. & Prasanna, S. R. M. (2012). Epoch extraction from emotional speech. In Proceedings of signal procesing & communications (SPCOM) (pp. 1\u20135).","DOI":"10.1109\/SPCOM.2012.6289995"},{"issue":"2","key":"9445_CR13","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1007\/s10772-012-9180-2","volume":"16","author":"D Govind","year":"2013","unstructured":"Govind, D., & Prasanna, S. R. M. (2013). Expressive speech synthesis: A review. International Journal of Speech Technology, 16(2), 237\u2013260.","journal-title":"International Journal of Speech Technology"},{"key":"9445_CR14","doi-asserted-by":"crossref","unstructured":"Govind, D. , Prasanna, S. R. M., & Yegnanarayana B. (2011). Neutral to target emotion conversion using source and suprasegmental information. In Proceedings of INTERSPEECH 2011.","DOI":"10.21437\/Interspeech.2011-743"},{"key":"9445_CR17","unstructured":"Haq, S., & Jackson, P. J. B. (2009). Speaker-dependent audio-visual emotion recognition. in Proceedings of international conference on audio visual speech processing (pp. 53\u201358)."},{"key":"9445_CR16","volume-title":"Machine audition: Principles, algorithms and systems","author":"S Haq","year":"2010","unstructured":"Haq, S., & Jackson, P. J. B. (2010). Chapter 17: Multimodal emotion recognition. In W. Wang (Ed.), Machine audition: Principles, algorithms and systems. Hershey: IGI Global Press."},{"key":"9445_CR18","doi-asserted-by":"crossref","unstructured":"Kadiri, S. R., Gangamohan, P., & Yegnanarayana, B. (2015). Analysis of excitation source features of speech for emotion recognition. in Proceedings of INTERSPEECH","DOI":"10.21437\/Interspeech.2015-329"},{"key":"9445_CR19","doi-asserted-by":"crossref","unstructured":"Kadiri, S. R. & Yegananarayana, B. (2015). Analysis of singing voice for epoch extraction using zero frequency filtering method,\u201d in International conference on acoustics, speech and signal processing (ICASSP).","DOI":"10.1109\/ICASSP.2015.7178774"},{"issue":"8","key":"9445_CR20","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1109\/TASL.2008.2004526","volume":"16","author":"KSR Murty","year":"2008","unstructured":"Murty, K. S. R., & Yegnanarayana, B. (2008). Epoch extraction from speech signals. IEEE Transactions on Audio Speech and Language Processing, 16(8), 1602\u20131614.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"issue":"6","key":"9445_CR21","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/LSP.2009.2016829","volume":"16","author":"KSR Murty","year":"2009","unstructured":"Murty, K. S. R., & Yegnanarayana, B. (2009). Characterization of glottal activity from speech signals. IEEE Signal Processing Letters, 16(6), 469\u2013472.","journal-title":"IEEE Signal Processing Letters"},{"issue":"1","key":"9445_CR22","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/s10772-010-9087-8","volume":"14","author":"D Pati","year":"2011","unstructured":"Pati, D., & Prasanna, S. R. M. (2011). Subsegmental, segmental and suprasegmental processing of linear prediction residual for speaker information. International Journal of Speech Technology, 14(1), 49\u201364.","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9445_CR23","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1109\/TASL.2013.2238529","volume":"21","author":"G Pradhan","year":"2013","unstructured":"Pradhan, G., & Prasanna, S. R. M. (2013). Speaker verification by vowel and nonvowel like segmentation. IEEE Transactions on Audio Speech and Language Processing, 21(4), 854\u2013867.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"9445_CR24","unstructured":"Prasanna, S. R. M. & Govind, D. (2010). Analysis of excitation source information in emotional speech,\u201d in Proceedings of the INTERSPEECH (pp. 781\u2013784)."},{"key":"9445_CR25","doi-asserted-by":"crossref","unstructured":"Prasanna, S. R. M., & Yegnanarayana, B. (2004). Extraction of pitch in adverse conditions. In Proceedings of ICASSP, Montreal.","DOI":"10.1109\/ICASSP.2004.1325934"},{"key":"9445_CR26","doi-asserted-by":"crossref","unstructured":"Prasanna, S. R. M., Govind, D., Rao, K. S., & Yenanarayana, B. (2010). Fast prosody modification using instants of significant excitation. In Proceedings of speech prosody.","DOI":"10.21437\/SpeechProsody.2010-126"},{"key":"9445_CR27","doi-asserted-by":"crossref","unstructured":"Pravena, D. & Govind D. (2017). Development of simulated emotion speech database for excitation source analysis,\u201d International Journal of Speech Technology. DOI:10.1007\/s10772-017-9407-3.","DOI":"10.1007\/s10772-017-9407-3"},{"key":"9445_CR28","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1109\/TSA.2005.858051","volume":"14","author":"KS Rao","year":"2006","unstructured":"Rao, K. S., & Yegnanarayana, B. (2006). Prosody modification using instants of significant excitation. IEEE Transactions on Audio Speech and Language Processing, 14, 972\u2013980.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"9445_CR29","doi-asserted-by":"crossref","unstructured":"Rao, K. S. & Yegnanarayana, B. Prosodic manipulation using instants of significant excitation. In Proceedings of ICASSP (pp. 528\u2013531).","DOI":"10.1109\/ICME.2003.1220936"},{"issue":"1","key":"9445_CR30","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"D Reynolds","year":"1995","unstructured":"Reynolds, D., & Rose, C. (1995). Robust text independent speaker recognition using gaussian mixture speaker models. IEEE Transactions on Audio Speech and Language Processing, 3(1), 72\u201383.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"9445_CR31","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Sonderegger A., Sauer J., & Lalanne D. (2013). Introducing the recola multimodal corpus of remote collaborative and affective interactions, In 2nd international workshop on emotion representation, analysis and synthesis in continuous time and space (EmoSPACE), in Proceedings of IEEE Face & Gestures.","DOI":"10.1109\/FG.2013.6553805"},{"key":"9445_CR32","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-1-84800-306-4_7","volume-title":"Affective information processing","author":"M Schroder","year":"2009","unstructured":"Schroder, M. (2009). Expressive speech synthesis: Past, present and possible futures. Affective information processing (pp. 111\u2013126). Berlin: Springer."},{"key":"9445_CR33","doi-asserted-by":"crossref","unstructured":"Whiteside, S. P. (1998). Simulated emotions: An acoustic study of voice and perturbation measures. Proceedings of the ICSLP, Sydney (pp. 699\u2013703).","DOI":"10.21437\/ICSLP.1998-141"},{"issue":"4","key":"9445_CR34","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1109\/TASL.2008.2012194","volume":"17","author":"B Yegnanarayana","year":"2009","unstructured":"Yegnanarayana, B., & Murty, K. S. R. (2009). Event-based instantaneous fundamental frequency estimation from speech signals. IEEE Transactions on Audio Speech and Language Processing, 17(4), 614\u2013625.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-017-9445-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9445-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9445-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T09:53:43Z","timestamp":1719395623000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-017-9445-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,17]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["9445"],"URL":"https:\/\/doi.org\/10.1007\/s10772-017-9445-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,8,17]]}}}