{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:03:48Z","timestamp":1766268228647,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,4,22]],"date-time":"2017-04-22T00:00:00Z","timestamp":1492819200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001409","name":"Department of Science and Technology, Ministry of Science and Technology","doi-asserted-by":"publisher","award":["SB\/FTP\/ETA-370\/2012"],"award-info":[{"award-number":["SB\/FTP\/ETA-370\/2012"]}],"id":[{"id":"10.13039\/501100001409","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s10772-017-9407-3","type":"journal-article","created":{"date-parts":[[2017,4,22]],"date-time":"2017-04-22T12:17:07Z","timestamp":1492863427000},"page":"327-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Development of simulated emotion speech database for excitation source analysis"],"prefix":"10.1007","volume":"20","author":[{"given":"D.","family":"Pravena","sequence":"first","affiliation":[]},{"given":"D.","family":"Govind","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,4,22]]},"reference":[{"key":"9407_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":"9407_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":"9407_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":"9407_CR5","unstructured":"Burkhardt, F., & Sendilmeier, W. F. (2000). Verification of acousical correlates of emotional speech using formant synthesis. In Proceedings of the ISCA Workshop on Speech & Emotion (pp. 151\u2013156)."},{"key":"9407_CR6","doi-asserted-by":"crossref","unstructured":"Cabral, J. P., & Oliveira, L. C. (2006). Emo voice: A system to generate emotions in speech. In Proceedings of INTERSPEECH (pp. 1798\u20131801).","DOI":"10.21437\/Interspeech.2006-497"},{"key":"9407_CR1","unstructured":"Cahn, J. E. (1989). Generation of affect in synthesized speech. In Proceedings of the American Voice I\/O Society (pp. 1\u201319)."},{"key":"9407_CR7","first-page":"497","volume":"87","author":"N Campbell","year":"2004","unstructured":"Campbell, N. (2004). Developments in corpus -based speech synthesis: Approaching natural conversational speech. IEICE Transactions on Information and Systems, 87, 497\u2013500.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"9407_CR8","doi-asserted-by":"crossref","unstructured":"Cowie, E.D., Cowie, R., Sneddon, I., Cox, C., Lowry, O., McRorie, M., Martin, J.-C., Devillers, L., Abrilian, S., Batliner, A., Amir, N., & Karpouzis, K. (2007). The humaine database: Addressing the collection and annotation of naturalistic and induced emotional data. In Proceedings of the Second International Conference on Affective Computing and Intelligent Interaction ( pp. 488\u2013500).","DOI":"10.1007\/978-3-540-74889-2_43"},{"issue":"4","key":"9407_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":"9407_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":"9407_CR11","unstructured":"Govind, D. (2013). Epoch based dynamic prosody modification for neutral to expressive speech conversion. Ph.D. dissertation, Indian Institute of Technology Guwahati."},{"key":"9407_CR12","doi-asserted-by":"crossref","unstructured":"Govind, D., Prasanna, S. R. M., & Yegnanarayana, B. (2011). \u201cNeutral to target emotion conversion using source and suprasegmental information. In Proceedings of INTERSPEECH, 2011.","DOI":"10.21437\/Interspeech.2011-743"},{"key":"9407_CR13","doi-asserted-by":"crossref","unstructured":"Govind, D., Prasanna, S. R. M. (2012). Epoch extraction from emotional speech. In Proceedings of the Signal Procesing & Communications (SPCOM) (pp. 1\u20135).","DOI":"10.1109\/SPCOM.2012.6289995"},{"key":"9407_CR14","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.21437\/Eurospeech.1997-494","volume":"1997","author":"JHL Hansen","year":"1997","unstructured":"Hansen, J. H. L., & Bou-Ghazale, S. E. (1997). Getting started with susas: A speech under simulated and actual stress database. EUROSPEECH, 1997, 1743\u20131746.","journal-title":"EUROSPEECH"},{"key":"9407_CR15","doi-asserted-by":"crossref","unstructured":"Hashizawa, Y., Hamzah, S. T. M. D., Ohyama, G. (2004). On the differences in prosodic features of emotional expressions in Japanese speech according to the degree of the emotion. In Proceedings of the Speech Prosody (pp. 655\u2013658).","DOI":"10.21437\/SpeechProsody.2004-151"},{"key":"9407_CR16","doi-asserted-by":"crossref","unstructured":"Hofer, G., Richmond, K., & Clark., R. (2005). Informed blending of databases for emotional speech synthesis. In Proceedings of INTERSPEECH.","DOI":"10.21437\/Interspeech.2005-326"},{"key":"9407_CR17","unstructured":"Jhonstone, T., & Scherer, K. R. (1999). The effects of emotions on voice quality. In Proceedings of the International Congress of Phoetic Sciences: San Fransisco (pp. 2029\u20132031)."},{"key":"9407_CR18","doi-asserted-by":"crossref","unstructured":"Kadiri, S.R., Gangamohan, P., Gangashetty, S.V., & Yegnanarayana, B. (2015). Analysis of excitation source features of speech for emotion recognition. In Proceedings of INTERSPEECH (pp. 1324\u20131328).","DOI":"10.21437\/Interspeech.2015-329"},{"key":"9407_CR19","first-page":"485","volume-title":"ch","author":"SG Koolagudi","year":"2009","unstructured":"Koolagudi, S. G., Maity, S., Kumar, V. A., Chakrabarti, S., Rao, K. S., Computing, Contemporary, et al. (2009). ch (pp. 485\u2013492). Speech Database for Emotion Analysis: IITKGP-SESC."},{"key":"9407_CR20","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s10772-010-9085-x","volume":"14","author":"SG Koolagudi","year":"2011","unstructured":"Koolagudi, S. G., & Rao, K. S. (2011). Two stage emotion recognition based on speaking rate. International Journal of Speech Technology, 14, 35\u201348.","journal-title":"International Journal of Speech Technology"},{"key":"9407_CR21","doi-asserted-by":"crossref","unstructured":"Kwon, O., Chan, K., Hao, J., Lee, S. T. (2003). Emotion recognition by speech signal. In Proceedings of the Eurospeech (pp. 125\u2013128).","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"9407_CR22","unstructured":"Liberman, M., Davis, K., Grossman, M., Martey, N., & Bell, J. (2002). LDC Emotional Prosody Speech Transcripts database, Univeristy of pennsylvania, Linguistic data consortium."},{"key":"9407_CR23","unstructured":"Lugger, M., Yang, B. (2009). Combining classifiers with diverse feature sets for robust speaker independent emotion recognition. In Proceedings of EUSIPCO."},{"issue":"1","key":"9407_CR24","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/T-AFFC.2011.20","volume":"3","author":"G McKeown","year":"2012","unstructured":"McKeown, G., Valstar, M., Pantic, M., & Schroder, M. (2012). The SEMAINE database: Annotated multimodal records of emotionally colorred conversations between a person and limited agent. IEEE Transactions on Affective Computing, 3(1), 5\u201317.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9407_CR25","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1121\/1.405558","volume":"93","author":"IR Murray","year":"1993","unstructured":"Murray, I. R., & Arnott, J. L. (1993). Towards the simulation of emotion in synthetic speech: A review of the literature on human vocal emotion. The Journal of the Acoustical Society of America, 93, 1097\u20131108.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"8","key":"9407_CR26","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":"9407_CR27","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., & Joseph, M. A. (2009). Characterization of glottal activity from speech signals. IEEE Signal Processing Letters, 16(6), 469\u2013472.","journal-title":"IEEE Signal Processing Letters"},{"key":"9407_CR28","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"T Nwe","year":"2003","unstructured":"Nwe, T., Foo, S., & Silva, L. D. (2003). Emotion recognition using hidden Markov models. Speech Communication, 41, 603\u2013623.","journal-title":"Speech Communication"},{"key":"9407_CR29","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":"9407_CR30","doi-asserted-by":"crossref","unstructured":"Prasanna, S. R. M. & Govind, D. (2010). Analysis of excitation source information in emotional speech. In Proceedings of INTERSPEECH (pp. 781\u2013784).","DOI":"10.21437\/Interspeech.2010-284"},{"key":"9407_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 Proceedings of IEEE Face & Gestures 2nd International Workshop on Emotion Representation, Analysis and Synthesis in Continuous Time and Space (EmoSPACE).","DOI":"10.1109\/FG.2013.6553805"},{"key":"9407_CR32","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1037\/0033-2909.99.2.143","volume":"99","author":"KR Scherer","year":"1986","unstructured":"Scherer, K. R. (1986). Vocal affect expressions: A review and a model for future research. Psychological Bulletin, 99, 143\u2013165.","journal-title":"Psychological Bulletin"},{"key":"9407_CR33","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-1-84800-306-4_7","volume":"2","author":"M Schroder","year":"2009","unstructured":"Schroder, M. (2009). Expressive speech synthesis: Past, present and possible futures. In Affective information processing. Springer, (vol. 2, pp. 111\u2013126).","journal-title":"Affective Information Processing, Springer"},{"key":"9407_CR34","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-6393(02)00049-3","volume":"39","author":"M Slaney","year":"2003","unstructured":"Slaney, M., & McRoberts, G. (2003). BabyEars: A recognition system for affective vocalizations. Speech Communication, 39, 367\u2013384.","journal-title":"Speech Communication"},{"key":"9407_CR35","doi-asserted-by":"crossref","unstructured":"Vroomen, J., Collier, R., Mozziconacci, S. J. L. (1993). Duration and intonation in emotional speech. In Proceedings of EUROSPEECH (pp. 577\u2013580).","DOI":"10.21437\/Eurospeech.1993-136"},{"issue":"5","key":"9407_CR36","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1007\/s00034-015-0134-1","volume":"35","author":"HK Vydana","year":"2016","unstructured":"Vydana, H. K., Kadiri, S. R., & Vuppala, A. K. (2016). Vowel-based non-uniform prosody modification for emotion conversion. Circuits, Systems and Signal Processing, 35(5), 1643\u20131663.","journal-title":"Circuits, Systems and Signal Processing"},{"key":"9407_CR37","doi-asserted-by":"crossref","unstructured":"Whiteside, S. P. (1998). Simulated emotions: An acoustic study of voice and perturbation measures. In Proceedings of ICSLP, Sydney, Australia (pp. 699\u2013703).","DOI":"10.21437\/ICSLP.1998-141"},{"key":"9407_CR38","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1121\/1.1913238","volume":"52","author":"CE Williams","year":"1972","unstructured":"Williams, C. E., & Stevens, K. (1972). Emotions and speech: Some acoustic correlates. The Journal of the Acoustical Society of America, 52, 1238\u20131250.","journal-title":"The Journal of the Acoustical Society of America"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-017-9407-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9407-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-017-9407-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T18:38:09Z","timestamp":1719167889000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-017-9407-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,22]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["9407"],"URL":"https:\/\/doi.org\/10.1007\/s10772-017-9407-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2017,4,22]]}}}