{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T12:54:25Z","timestamp":1773406465224,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2012,6,8]],"date-time":"2012-06-08T00:00:00Z","timestamp":1339113600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1007\/s10772-012-9150-8","type":"journal-article","created":{"date-parts":[[2012,6,7]],"date-time":"2012-06-07T14:07:01Z","timestamp":1339078021000},"page":"495-511","source":"Crossref","is-referenced-by-count":35,"title":["Emotion recognition from speech using sub-syllabic and pitch synchronous spectral features"],"prefix":"10.1007","volume":"15","author":[{"given":"Shashidhar G.","family":"Koolagudi","sequence":"first","affiliation":[]},{"given":"Sreenivasa Rao","family":"Krothapalli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,6,8]]},"reference":[{"key":"9150_CR1","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1016\/j.specom.2010.02.010","volume":"52","author":"D. Bitouk","year":"2010","unstructured":"Bitouk, D., Verma, R., & Nenkova, A. (2010). Class-level spectral features for emotion recognition. Speech Communication, 52, 613\u2013625.","journal-title":"Speech Communication"},{"key":"9150_CR2","first-page":"324","volume-title":"10th annual conference of the international speech communication association (interspeech)","author":"E. Bozkurt","year":"2009","unstructured":"Bozkurt, E., Erzin, E., Erdem, C. E., & Erdem, A. T. (2009). Improving automatic emotion recognition from speech signals. In 10th annual conference of the international speech communication association (interspeech), Brighton, UK, 6\u201310 September 2009 (pp.\u00a0324\u2013327)."},{"key":"9150_CR3","volume-title":"Interspeech","author":"F. Burkhardt","year":"2005","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., & Weiss, B. (2005). A database of German emotional speech. In Interspeech."},{"key":"9150_CR4","volume-title":"ACM 6th international conference on multimodal interfaces (ICMI 2004)","author":"C. Busso","year":"2004","unstructured":"Busso, C., Deng, Z., Yildirim, S., Bulut, M., Lee, C. M., Kazemzadeh, A., Lee, S., Neumann, U., & Narayanan, S. (2004). Analysis of emotion recognition using facial expressions, speech and multimodal information. In ACM 6th international conference on multimodal interfaces (ICMI 2004), State College, PA, The USA, October 2004."},{"key":"9150_CR5","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1109\/LSP.2003.821689","volume":"11","author":"J. Chen","year":"2004","unstructured":"Chen, J., Huang, Y. A., Li, Q., & Paliwal, K. K. (2004). Recognition of noisy speech using dynamic spectral subband centroids. IEEE Signal Processing Letters, 11, 258\u2013261 (February 2004).","journal-title":"IEEE Signal Processing Letters"},{"key":"9150_CR6","doi-asserted-by":"crossref","first-page":"1970","DOI":"10.1109\/ICSLP.1996.608022","volume-title":"4th international conference on spoken language processing","author":"F. Dellert","year":"1996","unstructured":"Dellert, F., Polzin, T., & Waibel, A. (1996). Recognizing emotion in speech. In 4th international conference on spoken language processing, Philadelphia, PA, USA, October 1996 (pp.\u00a01970\u20131973)."},{"key":"9150_CR7","volume-title":"Principal component neural networks: theory and applications","author":"K. I. Diamantaras","year":"1996","unstructured":"Diamantaras, K. I., & Kung, S. Y. (1996). Principal component neural networks: theory and applications. New York: Wiley."},{"key":"9150_CR8","volume-title":"Pattern classification","author":"R. O. Duda","year":"2004","unstructured":"Duda, R. O., Hart, P. E., & Stork, D. G. (2004). Pattern classification (2nd ed.). Singapore: Wiley-Interscience.","edition":"2"},{"key":"9150_CR9","volume-title":"INTERSPEECH","author":"S. V. Gangashetty","year":"2004","unstructured":"Gangashetty, S. V., Sekhar, C. C., & Yegnanarayana, B. (2004). Detection of vowel on set points in continuous speech using auto-associative neural network models. In INTERSPEECH. New York: IEEE Press."},{"key":"9150_CR10","first-page":"303","volume-title":"NOLISP","author":"S. V. Gangashetty","year":"2005","unstructured":"Gangashetty, S. V., Sekhar, C. C., & Yegnanarayana, B. (2005). Spotting multilingual consonant-vowel units of speech using neural network models. In M. Faundez-Zanuy (Ed.), NOLISP (pp.\u00a0303\u2013317). Berlin: Springer."},{"key":"9150_CR11","volume-title":"Int. joint conf. neural networks","author":"C. S. Gupta","year":"2002","unstructured":"Gupta, C. S., Prasanna, S. R. M., & Yegnanarayana, B. (2002). Autoassociative neural network models for online speaker verification using source features from vowels. In Int. joint conf. neural networks, Honululu, Hawii, USA, May 2002."},{"key":"9150_CR12","volume-title":"Neural networks: a comprehensive foundation","author":"S. Haykin","year":"1999","unstructured":"Haykin, S. (1999). Neural networks: a comprehensive foundation. New Delhi: Pearson Education Aisa."},{"key":"9150_CR13","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/11821830_4","volume-title":"Lecture notes in computer science. Intelligent virtual agents","author":"M. E. Hoque","year":"2006","unstructured":"Hoque, M. E., Yeasin, M., & Louwerse, M. M. (2006). Robust recognition of emotion from speech. In Lecture notes in computer science. Intelligent virtual agents (pp.\u00a042\u201353). Berlin: Springer."},{"key":"9150_CR14","first-page":"854","volume-title":"Int. joint conf. neural networks","author":"M. S. Ikbal","year":"1999","unstructured":"Ikbal, M. S., Misra, H., & Yegnanarayana, B. (1999). Analysis of autoassociative mapping neural networks. In Int. joint conf. neural networks, USA (pp.\u00a0854\u2013858)."},{"issue":"3","key":"9150_CR15","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/j.csl.2009.02.005","volume":"24","author":"A. I. Iliev","year":"2010","unstructured":"Iliev, A. I., Scordilis, M. S., Papa, J. P., & Falco, A. X. (2010). Spoken emotion recognition through optimum-path forest classification using glottal features. Computer Speech and Language, 24(3), 445\u2013460.","journal-title":"Computer Speech and Language"},{"issue":"9","key":"9150_CR16","first-page":"1","volume":"9","author":"N. Kamaruddin","year":"2009","unstructured":"Kamaruddin, N., & Wahab, A. (2009). Features extraction for speech emotion. Journal of Computational Methods in Science and Engineering, 9(9), 1\u201312.","journal-title":"Journal of Computational Methods in Science and Engineering"},{"key":"9150_CR17","first-page":"1548","volume-title":"Int. joint conf. neural networks (V2)","author":"S. P. Kishore","year":"2001","unstructured":"Kishore, S. P., & Yegnanarayana, B. (2001). Online text-independent speaker verification system using autoassociative neural network models. In Int. joint conf. neural networks (V2), Washington, USA, August 2001 (pp.\u00a01548\u20131553)."},{"key":"9150_CR18","unstructured":"Kodukula, S. R. M. (2009). Significance of excitation source information for speech analysis. Ph.D. thesis, Dept. of Computer Science, IIT, Madras (March 2009)."},{"key":"9150_CR19","volume-title":"Springer LNCS. The 3rd international conference on pattern recognition and machine intelligence (PReMI-09)","author":"S. G. Koolagudi","year":"2009","unstructured":"Koolagudi, S. G., & Rao, K. S. (2009). Exploring speech features for classifying emotions along valence dimension. In Springer LNCS. The 3rd international conference on pattern recognition and machine intelligence (PReMI-09)."},{"key":"9150_CR20","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s10772-010-9085-x","volume":"14","author":"S. G. 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":"9150_CR21","volume-title":"LNCS. Communications in computer and information science","author":"S. G. Koolagudi","year":"2009","unstructured":"Koolagudi, S. G., Maity, S., Kumar, V. A., Chakrabarti, S., & Rao, K. S. (2009). IITKGP-SESC: speech database for emotion analysis. In LNCS. Communications in computer and information science, August 2009. Berlin: Springer."},{"key":"9150_CR22","volume-title":"The 3rd international conference on contemporary computing","author":"S. G. Koolagudi","year":"2010","unstructured":"Koolagudi, S. G., Ray, S., & Rao, K. S. (2010). Emotion classification based on speaking rate. In The 3rd international conference on contemporary computing."},{"key":"9150_CR23","doi-asserted-by":"crossref","first-page":"125","DOI":"10.21437\/Eurospeech.2003-80","volume-title":"Eurospeech","author":"O. Kwon","year":"2003","unstructured":"Kwon, O., Chan, K., Hao, J., & Lee, T. (2003). Emotion recognition by speech signals. In Eurospeech, Geneva (pp.\u00a0125\u2013128)."},{"key":"9150_CR24","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","volume":"13","author":"C. M. Lee","year":"2005","unstructured":"Lee, C. M., & Narayanan, S. (2005). Toward detecting emotions in spoken dialogs. IEEE Transactions on Speech and Audio Processing, 13, 293\u2013303 (March 2005).","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9150_CR25","volume-title":"INTERSPEECH-2010","author":"S. H. R. Mallidi","year":"2010","unstructured":"Mallidi, S. H. R., Prahallad, K., Gangashetty, S. V., & Yegnanarayana, B. (2010). Significance of pitch synchronous analysis for speaker recognition using AANN models. In INTERSPEECH-2010, Makuhari, Japan, September 2010."},{"key":"9150_CR26","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1016\/j.specom.2008.04.010","volume":"50","author":"L. Mary","year":"2008","unstructured":"Mary, L., & Yegnanarayana, B. (2008). Extraction and representation of prosodic features for language and speaker recognition. Speech Communication, 50, 782\u2013796 (April 2008).","journal-title":"Speech Communication"},{"key":"9150_CR27","volume-title":"ISCA workshop on speech and emotion","author":"S. McGilloway","year":"2000","unstructured":"McGilloway, S., Cowie, R., Douglas-Cowie, E., Gielen, S., Westerdijk, M., & Stroeve, S. (2000). Approaching automatic recognition of emotion from voice: a rough benchmark. In ISCA workshop on speech and emotion, Belfast."},{"key":"9150_CR28","volume-title":"8th international symposium on signal processing and its applications","author":"O. M. Mubarak","year":"2005","unstructured":"Mubarak, O. M., Ambikairajah, E., & Epps, J. (2005). Analysis of an MFCC-based audio indexing system for efficient coding of multimedia sources. In 8th international symposium on signal processing and its applications, Sydney, Australia, August 2005."},{"key":"9150_CR29","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1109\/TASL.2008.2004526","volume":"16","author":"K. S. R. 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, 1602\u20131613.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9150_CR30","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1121\/1.396628","volume":"84","author":"H. Muta","year":"1988","unstructured":"Muta, H., Baer, T., Wagatsuma, K., Muraoka, T., & Fukuda, H. (1988a). Pitch synchronous analysis of hoarseness in running speech. The Journal of the Acoustical Society of America, 84, 1292\u20131301.","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9150_CR31","unstructured":"Muta, H., Baer, T., Wagatsuma, K., Muraoka, T., & Fukudatt, H. (1988b). A pitch-synchronous analysis of hoarseness in running speech. Status report on speech research SR-93\/94, Haskins laboratories."},{"key":"9150_CR32","first-page":"809","volume-title":"INTERSPEECH 2006\u2014ICSLP","author":"D. Neiberg","year":"2006","unstructured":"Neiberg, D., Elenius, K., & Laskowski, K. (2006). Emotion recognition in spontaneous speech using GMMs. In INTERSPEECH 2006\u2014ICSLP, Pittsburgh, Pennsylvania, 17\u201319 September 2006 (pp.\u00a0809\u2013812)."},{"key":"9150_CR33","first-page":"495","volume-title":"6th international conference on neural information processing (ICONIP-99)","author":"J. Nicholson","year":"1999","unstructured":"Nicholson, J., Takahashi, K., & Nakatsu, R. (1999). Emotion recognition in speech using neural networks. In 6th international conference on neural information processing (ICONIP-99), Perth, WA, Australia, August 1999 (pp.\u00a0495\u2013501)."},{"key":"9150_CR34","series-title":"ACII","first-page":"279","volume-title":"LNCS","author":"T. L. Pao","year":"2005","unstructured":"Pao, T. L., Chen, Y. T., Yeh, J. H., & Liao, W. Y. (2005). Combining acoustic features for improved emotion recognition in Mandarin speech. In J. Tao, T. Tan & R. Picard (Eds.), LNCS. ACII (pp.\u00a0279\u2013285). Berlin: Springer."},{"key":"9150_CR35","series-title":"ACII 2007","volume-title":"LNCS","author":"T. L. Pao","year":"2007","unstructured":"Pao, T. L., Chen, Y. T., Yeh, J. H., Cheng, Y. M., & Chien, C. S. (2007). Feature combination for better differentiating anger from neutral in mandarin emotional speech. In LNCS: Vol.\u00a04738. ACII 2007. Berlin: Springer."},{"key":"9150_CR36","volume-title":"Proceedings of the 1999 conference on artificial neural networks in engineering (ANNIE 99)","author":"V. A. Petrushin","year":"1999","unstructured":"Petrushin, V. A. (1999). Emotion in speech: recognition and application to call centers. In Proceedings of the 1999 conference on artificial neural networks in engineering (ANNIE 99)."},{"key":"9150_CR37","volume-title":"Proceedings workshop on spoken language","author":"S. R. M. Prasanna","year":"2003","unstructured":"Prasanna, S. R. M., Zachariah, J. M., & Yegnanarayana, B. (2003). Begin-end detection using vowel onset points. In Proceedings workshop on spoken language, TIFR Mumbai, India (January 2003)."},{"key":"9150_CR38","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1016\/j.specom.2006.06.002","volume":"48","author":"S. M. Prasannaa","year":"2006","unstructured":"Prasannaa, S. M., Gupta, C. S., & Yegnanarayana, B. (2006). Extraction of speaker-specific excitation information from linear prediction residual of speech. Speech Communication, 48, 1243\u20131261.","journal-title":"Speech Communication"},{"key":"9150_CR39","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1109\/TASL.2008.2010884","volume":"17","author":"S. R. M. Prasanna","year":"2009","unstructured":"Prasanna, S. R. M., Reddy, B. V. S., & Krishnamoorthy, P. (2009). Vowel onset point detection using source, spectral peaks, and modulation spectrum energies. IEEE Transactions on Audio, Speech, and Language Processing, 17, 556\u2013565 (May 2009).","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9150_CR40","volume-title":"Fundamentals of speech recognition","author":"L. R. Rabiner","year":"1993","unstructured":"Rabiner, L. R., & Juang, B. H. (1993). Fundamentals of speech recognition. Englewood Cliffs: Prentice-Hall."},{"key":"9150_CR41","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/j.csl.2009.03.003","volume":"24","author":"K. S. Rao","year":"2010","unstructured":"Rao, K. S. (2010). Voice conversion by mapping the speaker-specific features using pitch synchronous approach. Computer Speech and Language, 24, 474\u2013494.","journal-title":"Computer Speech and Language"},{"key":"9150_CR42","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10772-010-9086-9","volume":"14","author":"K. S. Rao","year":"2011","unstructured":"Rao, K. S. (2011a). Application of prosody models for developing speech systems in Indian languages. International Journal of Speech Technology, 14, 19\u201333.","journal-title":"International Journal of Speech Technology"},{"key":"9150_CR43","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1007\/s12046-011-0047-z","volume":"36","author":"K. S. Rao","year":"2011","unstructured":"Rao, K. S. (2011b). Role of neural network models for developing speech systems. Sadhana (Springer), 36, 783\u2013836.","journal-title":"Sadhana (Springer)"},{"issue":"4","key":"9150_CR44","first-page":"24","volume":"9","author":"K. S. Rao","year":"2011","unstructured":"Rao, K. S., & Koolagudi, S. G. (2011). Identification of Hindi dialects and emotions using spectral and prosodic features of speech. Journal of Systemics, Cybernetics and Informatics, 9(4), 24\u201333.","journal-title":"Journal of Systemics, Cybernetics and Informatics"},{"key":"9150_CR45","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1109\/TSA.2005.858051","volume":"14","author":"K. S. Rao","year":"2006","unstructured":"Rao, K. S., & Yegnanarayana, B. (2006). Prosody modification using instants of significant excitation. IEEE Transactions on Speech and Audio Processing, 14, 972\u2013980 (May 2006).","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9150_CR46","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1016\/j.specom.2009.06.004","volume":"51","author":"K. S. Rao","year":"2009","unstructured":"Rao, K. S., & Yegnanarayana, B. (2009). Duration modification using glottal closure instants and vowel onset points. Speech Communication, 51, 1263\u20131269.","journal-title":"Speech Communication"},{"key":"9150_CR47","unstructured":"Reddy, K. S. (2004). Source and system features for speaker recognition. Master\u2019s thesis, MS thesis, Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai 600 036, India 2004."},{"key":"9150_CR48","volume-title":"TENCON 2008\u20142008 IEEE region 10 conference, IIIT","author":"B. V. S. Reddy","year":"2008","unstructured":"Reddy, B. V. S., Rao, K. V., & Prasanna, S. R. M. (2008). Keyword spotting using vowel onset point, vector quantization and hidden Markov modeling based techniques. In TENCON 2008\u20142008 IEEE region 10 conference, IIIT, Hyderabad. New York: IEEE Press."},{"key":"9150_CR49","first-page":"577","volume-title":"Proc. IEEE int. conf. acoust., speech, signal processing","author":"B. Schuller","year":"2004","unstructured":"Schuller, B., Rigoll, G., & Lang, M. (2004). Speech emotion recognition combining acoustic features and linguistic information in a hybrid support vector machine-belief network architecture. In Proc. IEEE int. conf. acoust., speech, signal processing (pp.\u00a0577\u2013580). New York: IEEE Press."},{"key":"9150_CR50","first-page":"170","volume":"7","author":"M. Sigmund","year":"2007","unstructured":"Sigmund, M. (2007). Spectral analysis of speech under stress. IJCSNS International Journal of Computer Science and Network Security, 7, 170\u2013172.","journal-title":"IJCSNS International Journal of Computer Science and Network Security"},{"key":"9150_CR51","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","volume":"48","author":"D. Ververidis","year":"2006","unstructured":"Ververidis, D., & Kotropoulos, C. (2006). Emotional speech recognition: resources, features, and methods. Speech Communication, 48, 1162\u20131181.","journal-title":"Speech Communication"},{"key":"9150_CR52","first-page":"I593","volume-title":"ICASSP","author":"D. Ververidis","year":"2004","unstructured":"Ververidis, D., Kotropoulos, C., & Pitas, I. (2004). Automatic emotional speech classification. In ICASSP (pp.\u00a0I593\u2013I596). New York: IEEE Press."},{"key":"9150_CR53","author":"A. K. Vuppala","year":"2012","unstructured":"Vuppala, A. K., Rao, K. S., & Chakrabarti, S. (2012a). Improved vowel onset point detection using epoch intervals. International Journal of Electronics and Communications. doi: 10.1016\/j.aeue.2 .","journal-title":"International Journal of Electronics and Communications"},{"key":"9150_CR54","doi-asserted-by":"crossref","first-page":"1894","DOI":"10.1109\/TASL.2012.2191284","volume":"20","author":"A. K. Vuppala","year":"2012","unstructured":"Vuppala, A. K., Yadav, J., Chakrabarti, S., & Rao, K. S. (2012b). Vowel onset point detection for low bit rate coded speech. IEEE Transactions on Audio, Speech, and Language Processing, 20, 1894\u20131903 (August 2012).","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9150_CR55","first-page":"1","volume-title":"16th international conference on digital signal processing","author":"S. Wu","year":"2009","unstructured":"Wu, S., Falk, T. H., & Chan, W. Y. (2009). Automatic recognition of speech emotion using long-term spectro-temporal features. In 16th international conference on digital signal processing, Santorini-Hellas, 5\u20137 July 2009 (pp. 1\u20136). New York: IEEE Press."},{"key":"9150_CR56","volume-title":"Artificial neural networks","author":"B. Yegnanarayana","year":"1999","unstructured":"Yegnanarayana, B. (1999). Artificial neural networks. New Delhi: Prentice-Hall."},{"key":"9150_CR57","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/S0893-6080(02)00019-9","volume":"15","author":"B. Yegnanarayana","year":"2002","unstructured":"Yegnanarayana, B., & Kishore, S. P. (2002). AANN an alternative to GMM for pattern recognition. Neural Networks, 15, 459\u2013469.","journal-title":"Neural Networks"},{"key":"9150_CR58","volume-title":"IEEE int. conf. acoust., speech, and signal processing","author":"B. Yegnanarayana","year":"2001","unstructured":"Yegnanarayana, B., Reddy, K. S., & Kishore, S. P. (2001a). Source and system features for speaker recognition using aann models. In IEEE int. conf. acoust., speech, and signal processing, Salt Lake City, UT, May 2001."},{"key":"9150_CR59","first-page":"409","volume-title":"Proc. IEEE int. conf. acoust., speech, signal processing","author":"B. Yegnanarayana","year":"2001","unstructured":"Yegnanarayana, B., Reddy, K. S., & Kishore, S. P. (2001b). Source and system features for speaker recognition using AANN models. In Proc. IEEE int. conf. acoust., speech, signal processing, Salt Lake City, Utah, USA, May 2001 (pp.\u00a0409\u2013412)."},{"key":"9150_CR60","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1109\/ICNC.2007.555","volume-title":"Third international conference on natural computation","author":"Y. Zeng","year":"2007","unstructured":"Zeng, Y., Wu, H., & Gao, R. (2007). Pitch synchronous analysis method and Fisher criterion based speaker identification. In Third international conference on natural computation, Washington D.C., USA (pp.\u00a0691\u2013695). Los Alamitos: IEEE Comput. Soc."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9150-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-012-9150-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-012-9150-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T05:55:38Z","timestamp":1687499738000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-012-9150-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,8]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2012,12]]}},"alternative-id":["9150"],"URL":"https:\/\/doi.org\/10.1007\/s10772-012-9150-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,8]]}}}