{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:25:27Z","timestamp":1790702727494,"version":"4.1.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10772-021-09897-x","type":"journal-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T12:04:38Z","timestamp":1632139478000},"page":"197-204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Handling emotional speech: a prosody based data augmentation technique for improving neutral speech trained ASR systems"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9276-0511","authenticated-orcid":false,"given":"Pavan Raju","family":"Kammili","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B. H. V. S.","family":"Ramakrishnam Raju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. Sri","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,20]]},"reference":[{"issue":"3","key":"9897_CR1","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1109\/LSP.2009.2038507","volume":"17","author":"N Dhananjaya","year":"2010","unstructured":"Dhananjaya, N., & Yegnanarayana, B. (2010). Voiced\/nonvoiced detection based on robustness of voiced epochs. IEEE Signal Processing Letters, 17(3), 273\u2013276.","journal-title":"IEEE Signal Processing Letters"},{"key":"9897_CR2","doi-asserted-by":"crossref","unstructured":"Gangamohan, P., Mittal, V., & Yegnanarayana, B. (2012). Relative importance of different components of speech contributing to perception of emotion. In Speech Prosody.","DOI":"10.21437\/SpeechProsody.2012-164"},{"issue":"6","key":"9897_CR3","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"H Geoffrey","year":"2012","unstructured":"Geoffrey, H., Li, D., Dong, Y., George, E. D., & Mohamed, A.-R. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine, 29(6), 82\u201397.","journal-title":"IEEE Signal Processing Magazine"},{"key":"9897_CR4","doi-asserted-by":"crossref","unstructured":"Gerosa, M., Giuliani, D., Narayanan, S., & Potamianos, A. (2009). A review of asr technologies for children\u2019s speech. In Proceedings of the 2nd workshop on child, computer and interaction. (pp. 1\u20138).","DOI":"10.1145\/1640377.1640384"},{"key":"9897_CR5","doi-asserted-by":"crossref","unstructured":"Hsiao, R., Ma, J., Hartmann, W., Karafi\u00e1t, M., Gr\u00e9zl, F., Burget, L., Sz\u00f6ke, I., \u010cernock\u1ef3, J. H., Watanabe, S., Chen, Z., et al. (2015). Robust speech recognition in unknown reverberant and noisy conditions. In Workshop on automatic speech recognition and understanding (ASRU) (pp. 533\u2013538). IEEE.","DOI":"10.1109\/ASRU.2015.7404841"},{"key":"9897_CR6","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Seltzer, M.\u00a0L., & \u00a0Khudanpur, S. (2017) A study on data augmentation of reverberant speech for robust speech recognition. In International conference on acoustics, speech and signal processing (ICASSP). (pp. 5220\u20135224). IEEE","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"9897_CR7","doi-asserted-by":"crossref","unstructured":"Koolagudi, S.\u00a0G., Maity, S., Kumar, V.\u00a0A., Chakrabarti, S.& Rao, K.\u00a0S. (2009) Iitkgp-sesc: Speech database for emotion analysis. In International conference on contemporary computing. (pp. 485\u2013492). Springer.","DOI":"10.1007\/978-3-642-03547-0_46"},{"key":"9897_CR8","doi-asserted-by":"crossref","unstructured":"Lippmann, R., Martin, E., & Paul, D. (1987) Multi-style training for robust isolated-word speech recognition. In International conference on acoustics, speech, and signal processing (ICASSP), (vol.\u00a012, pp. 705\u2013708). IEEE","DOI":"10.1109\/ICASSP.1987.1169544"},{"issue":"8","key":"9897_CR9","doi-asserted-by":"publisher","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\u20131613.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9897_CR10","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) Librispeech: An asr corpus based on public domain audio books. In International conference on acoustics, speech and signal processing (ICASSP). (pp. 5206\u20135210). IEEE.","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"9897_CR11","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Chen, G., Manohar, V., Ko, T., Povey, D., & Khudanpur, S. (2015). Jhu aspire system: Robust lvcsr with tdnns, ivector adaptation and rnn-lms. In Workshop on automatic speech recognition and understanding (ASRU), (pp. 539\u2013546)","DOI":"10.1109\/ASRU.2015.7404842"},{"key":"9897_CR12","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P. et\u00a0al. (2011) The kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society."},{"key":"9897_CR13","doi-asserted-by":"crossref","unstructured":"Prasanna, S., Govind, D., Rao, K. S., & Yegnanarayana, B. (2010). Fast prosody modification using instants of significant excitation. In Proceedings of Fifth International Conference of Speech Prosody.","DOI":"10.21437\/SpeechProsody.2010-126"},{"key":"9897_CR14","doi-asserted-by":"crossref","unstructured":"Raju, V. V., Gangamohan, P., Gangashetty, S. V., & Vuppala, A. K. (2016). Application of prosody modification for speech recognition in different emotion conditions. In IEEE Region 10 Conference (TENCON), IEEE, 2016 (pp. 951\u2013954).","DOI":"10.1109\/TENCON.2016.7848145"},{"key":"9897_CR15","doi-asserted-by":"crossref","unstructured":"Raju, V. V., Vydana, H. K., Gangashetty, S. V., & Vuppala, A. K. (2017) Importance of non-uniform prosody modification for speech recognition in emotion conditions, In 2017 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC). (pp. 573\u2013576). IEEE.","DOI":"10.1109\/APSIPA.2017.8282109"},{"issue":"10","key":"9897_CR16","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1109\/LSP.2007.896454","volume":"14","author":"KS Rao","year":"2007","unstructured":"Rao, K. S., Prasanna, S. M., & Yegnanarayana, B. (2007). Determination of instants of significant excitation in speech using hilbert envelope and group delay function. IEEE Signal Processing Letters, 14(10), 762\u2013765.","journal-title":"IEEE Signal Processing Letters"},{"key":"9897_CR17","unstructured":"Rousseau, A., Del\u00e9glise, P., & Esteve, Y. (2012). Ted-lium: An automatic speech recognition dedicated corpus. In LREC (pp. 125\u2013129)."},{"key":"9897_CR18","unstructured":"Russell, M., & D\u2019Arcy, S. (2007). Challenges for computer recognition of children\u2019s speech. In Workshop on speech and language technology in education."},{"key":"9897_CR19","doi-asserted-by":"crossref","unstructured":"Schalkwyk, J., Beeferman, D., Beaufays, F., Byrne, B., Chelba, C., Cohen, M., Kamvar, M., & Strope, B. (2010) \u201cYour word is my command\u201d: Google search by voice: A case study. In Advances in speech recognition. (pp. 61\u201390). Springer.","DOI":"10.1007\/978-1-4419-5951-5_4"},{"key":"9897_CR20","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.patrec.2019.12.019","volume":"131","author":"S Shahnawazuddin","year":"2020","unstructured":"Shahnawazuddin, S., Adiga, N., Kathania, H. K., & Sai, B. T. (2020). Creating speaker independent asr system through prosody modification based data augmentation. Pattern Recognition Letters, 131, 213\u2013218.","journal-title":"Pattern Recognition Letters"},{"issue":"5","key":"9897_CR21","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1109\/89.466662","volume":"3","author":"R Smits","year":"1995","unstructured":"Smits, R., & Yegnanarayana, B. (1995). Determination of instants of significant excitation in speech using group delay function. IEEE Transactions on Speech and Audio Processing, 3(5), 325\u2013333.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9897_CR22","doi-asserted-by":"crossref","unstructured":"Srivastava, B. M. L., Sitaram, S., Mehta, R. K., Mohan, K. D., Matani, P., Satpal, S., Bali, K., Srikanth, R., & Nayak, N. (2018). Interspeech 2018 low resource automatic speech recognition challenge for indian languages. In SLTU (pp. 11\u201314).","DOI":"10.21437\/SLTU.2018-3"},{"key":"9897_CR24","doi-asserted-by":"crossref","unstructured":"Vegesna, V. V. R., Gurugubelli, K., & Vuppala, A. K. (2018). Prosody modification for speech recognition in emotionally mismatched conditions. International Journal of Speech Technology, 21(3), 521\u2013532.","DOI":"10.1007\/s10772-018-9503-z"},{"issue":"1","key":"9897_CR23","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s11036-018-1052-9","volume":"24","author":"VVR Vegesna","year":"2019","unstructured":"Vegesna, V. V. R., Gurugubelli, K., & Vuppala, A. K. (2019). Application of emotion recognition and modification for emotional telugu speech recognition. Mobile Networks and Applications, 24(1), 193\u2013201.","journal-title":"Mobile Networks and Applications"},{"key":"9897_CR25","unstructured":"Vishnu Vidyadhara Raju, V. (2020). Towards building a robust Telugu ASR system for emotional speech. PhD Thesis. http:\/\/hdl.handle.net\/10603\/306355"},{"key":"9897_CR26","volume-title":"Automatic Speech Recognition","author":"D Yu","year":"2016","unstructured":"Yu, D., & Deng, L. (2016). Automatic speech recognition. Springer."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09897-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09897-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09897-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:51:13Z","timestamp":1725810673000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09897-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,20]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["9897"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09897-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,20]]},"assertion":[{"value":"2 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}