{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T22:27:58Z","timestamp":1784672878941,"version":"3.55.0"},"reference-count":62,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2003,11,1]],"date-time":"2003-11-01T00:00:00Z","timestamp":1067644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2003,11]]},"DOI":"10.1016\/s0167-6393(03)00099-2","type":"journal-article","created":{"date-parts":[[2003,8,1]],"date-time":"2003-08-01T01:24:25Z","timestamp":1059701065000},"page":"603-623","source":"Crossref","is-referenced-by-count":702,"title":["Speech emotion recognition using hidden Markov models"],"prefix":"10.1016","volume":"41","author":[{"given":"Tin Lay","family":"Nwe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Say Wei","family":"Foo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyanage C","family":"De Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(03)00099-2_BIB1","unstructured":"Arnold, M.B., 1960. Emotion and Personality. Physiological Aspects, Vol. 2. Columbia University Press, New York"},{"issue":"6","key":"10.1016\/S0167-6393(03)00099-2_BIB2","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1121\/1.1914702","article-title":"Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification","volume":"55","author":"Atal","year":"1974","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB3","series-title":"Speech Recognition Theory and C++ Implementation","author":"Becchetti","year":"1998"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB4","first-page":"1","article-title":"The generation of affect in synthesized speech","volume":"8","author":"Cahn","year":"1990","journal-title":"J. Amer. Voice I\/O Soc."},{"issue":"6","key":"10.1016\/S0167-6393(03)00099-2_BIB5","doi-asserted-by":"crossref","first-page":"3392","DOI":"10.1121\/1.410601","article-title":"Nonlinear analysis and classification of speech under stressed conditions","volume":"96","author":"Cairns","year":"1994","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB6","unstructured":"Coleman, R., Williams, R., 1979. Identification of emotional states using perceptual and acoustic analyses. In: Lawrence, V., Weinberg, B. (Eds.), Care of the Professional Voice, Vol. 1. The Voice Foundation, New York"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB7","series-title":"The Science of Emotion","author":"Cornelius","year":"1996"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB8","unstructured":"Cowan, M., 1936. Pitch and Intensity Characteristics of Stage of Speech. Arch. Speech, suppl. to Dec. issue"},{"issue":"1","key":"10.1016\/S0167-6393(03)00099-2_BIB9","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/79.911197","article-title":"Emotion recognition in human\u2013computer interaction","volume":"18","author":"Cowie","year":"2001","journal-title":"IEEE Sig. Proc. Mag."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB10","series-title":"Prosodic Systems and Intonation in English","author":"Crystal","year":"1969"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB11","series-title":"The English Tone of Voice","author":"Crystal","year":"1975"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB12","doi-asserted-by":"crossref","unstructured":"Darwin, C., 1965. The Expression of Emotions in Man and Animals. John Murray, Ed., 1872. Reprinted by University Press","DOI":"10.1037\/10001-000"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB13","series-title":"Recognition of Facial Expressions","author":"Davis","year":"1975"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB14","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB15","series-title":"The Communication of Emotional Meaning","year":"1964"},{"issue":"1","key":"10.1016\/S0167-6393(03)00099-2_BIB16","first-page":"105","article-title":"Use of multimodal information in facial emotion recognition","volume":"E81-D","author":"De Silva","year":"1998","journal-title":"IEICE Trans. Inf. Syst."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB17","doi-asserted-by":"crossref","unstructured":"Dellaert, F., Polzin, T., Waibel, A., 1996. Recognizing Emotion in Speech. Fourth International Conference on Spoken Language Processing 3, 1970\u20131973","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB18","series-title":"Discrete-Time Processing of Speech Signals","author":"Deller","year":"1993"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB19","series-title":"Darwin and Facial Expressions","author":"Ekman","year":"1973"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB20","series-title":"Unmasking the Face","author":"Ekman","year":"1975"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB21","unstructured":"Elias, N.J., 1975. New Statistical Methods for Assigning Device Tolerances. Proc. IEEE Int. SYmp. Ccts. Sys., 1975, Newton, MA, USA, pp. 329\u2013332"},{"issue":"10","key":"10.1016\/S0167-6393(03)00099-2_BIB22","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1109\/29.35395","article-title":"A new vector quantization clustering algorithm","volume":"37","author":"Equitz","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB23","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1080\/03637753909374863","article-title":"An experimental study of the pitch characteristics of the voice during the expression of emotion","volume":"6","author":"Fairbanks","year":"1939","journal-title":"Speech Monograph"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB24","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1177\/002383097802100102","article-title":"A new method of investigating the perception of prosodic features","volume":"21","author":"Fonagy","year":"1978","journal-title":"Language and Speech"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB25","doi-asserted-by":"crossref","unstructured":"Fonagy, I., 1978b. In: Sundberg, J. (Ed.), Emotions, Voice and Music in Language and Speech, Vol. 21, pp. 34\u201349","DOI":"10.1177\/002383097802100102"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB26","first-page":"293","article-title":"Emotional patterns in intonation and music","volume":"16","author":"Fonagy","year":"1963","journal-title":"Z. Phonet. Sprachwiss. Kommunikationsforsch"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB27","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1037\/0003-066X.46.8.863","article-title":"If it\u2019s not left it\u2019s right","volume":"46","author":"Fox","year":"1992","journal-title":"Amer. Psychol."},{"issue":"3","key":"10.1016\/S0167-6393(03)00099-2_BIB28","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1037\/0033-2909.97.3.412","article-title":"Communicating Emotion: The Role of Prosodic Features","volume":"97","author":"Frick","year":"1985","journal-title":"Psychol. Bull."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB29","series-title":"Digital Speech Processing, Synthesis and Recognition","author":"Furui","year":"1989"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB30","first-page":"33","article-title":"Changes of the voice expression during suggestively influenced states of experiencing","volume":"21","author":"Havrdova","year":"1979","journal-title":"Activitas Nervosa Superior"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB31","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1044\/jshr.1103.481","article-title":"Relations between prosodic variables and emotions in normal american english utterances","volume":"11","author":"Huttar","year":"1968","journal-title":"J. Speech Hearing Res."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB32","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1001\/archpsyc.1986.01800030098011","article-title":"Recognition of emotion from vocal cues","volume":"43","author":"Johnson","year":"1986","journal-title":"Arch. Gen. Psych."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB33","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/BF00869311","article-title":"Communication of affects by single vowels","volume":"14","author":"Kaiser","year":"1962","journal-title":"Synthese"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB34","first-page":"208","article-title":"Acoustic correlates of the emotional content of vocalized speech","volume":"22","author":"Kotlyar","year":"1976","journal-title":"J. Acoust. Acad. Sci. USSR"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB35","series-title":"Emotion Adaptation","author":"Lazarus","year":"1991"},{"issue":"11","key":"10.1016\/S0167-6393(03)00099-2_BIB36","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","article-title":"Speaker-independent phone recognition using Hidden Markov Models","volume":"37","author":"Lee","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB37","first-page":"9","article-title":"A phonophotographic study of trained and untrained voices reading factual and dramatic material","volume":"1","author":"Lynch","year":"1934","journal-title":"Arch. Speech"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB38","unstructured":"McGilloway, S., Cowie, R., Douglas-Cowie, E., 1995. Prosodic signs of emotion in speech: preliminary results from a new technique for automatic statistical analysis. In: Proc. XIIIth Int. Congr. Phonetic Sciences, Vol. 1. Stockholm, Sweden, pp. 250\u2013253"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB39","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. ISCA Workshop on Speech and Emotion, Belfast"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB40","unstructured":"Muller, A., 1960. Experimentelle Untersuchungen zur stimmlichen Darstellung von Gefuehlen [Experimental Studies on Vocal Portrayal of Emotion], Ph.D. dissertation, Univ. Gottingen, Germany"},{"issue":"2","key":"10.1016\/S0167-6393(03)00099-2_BIB41","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1121\/1.405558","article-title":"Toward the simulation of emotion in synthetic speech: A review of the literature on human vocal emotion","volume":"93","author":"Murray","year":"1993","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB42","doi-asserted-by":"crossref","unstructured":"Nicholson, J., Takahashi, K., Nakatsu, R., 1999. Emotion recognition in speech using neural networks. 6th International Conference on Neural Information Processing, ICONIP \u201999, Vol. 2, pp. 495\u2013501","DOI":"10.1109\/ICONIP.1999.845644"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB43","series-title":"Goals and Affect","article-title":"Communicative theory of emotions: Empirical test, mental models and implications for social interaction","author":"Oatley","year":"1995"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB44","series-title":"Intonation of Colloquial English","author":"O\u2019Connor","year":"1973"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB45","unstructured":"Oster, A., Risberg, A., 1986. The Identification of the Mood of A Speaker by Hearing Impaired Listeners. Speech Transmission Lab. Quarterly Progress Status Report 4, Stockholm, pp. 79\u201390"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB46","series-title":"Understanding Emotions","author":"Otaley","year":"1996"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB47","series-title":"The Psychology and Biology of Emotion","author":"Plutchik","year":"1994"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB48","series-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB49","series-title":"Digital Processing of Speech Signals","author":"Rabiner","year":"1978"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB50","series-title":"Approaches to Emotion","article-title":"On the nature and function of emotion: A component process approach","author":"Scherer","year":"1984"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB51","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1037\/0033-2909.99.2.143","article-title":"Vocal effect expression: A review and a model for future research","volume":"99","author":"Scherer","year":"1986","journal-title":"Psychol. Bull."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB52","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1037\/0033-2909.99.2.143","article-title":"Vocal affect expression: A review and a model for future research","volume":"99","author":"Scherer","year":"1986","journal-title":"Psychol. Bull."},{"issue":"1","key":"10.1016\/S0167-6393(03)00099-2_BIB53","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1177\/0022022101032001009","article-title":"Emotion inferences from vocal expression correlate across languages and cultures","volume":"32","author":"Scherer","year":"2001","journal-title":"J. Cross-Cultural Psychol."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB54","series-title":"Approaches to Emotion","author":"Scherer","year":"1984"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB55","series-title":"English Intonation. Its Form and Function","author":"Schubiger","year":"1958"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB56","first-page":"215","article-title":"Emotional changes in human voice","volume":"19","author":"Sulc","year":"1977","journal-title":"Activitas Nervosa Superior"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB57","series-title":"Der Ausdruck der Sprechstimme","author":"Trojan","year":"1952"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB58","unstructured":"Utsuki, N., Okamura, N., 1976. Relationship Between Emotional State and Fundamental Frequency of Speech. Rep. Aeromedical Laboratory. Japan Air Self-Defense Force 16, 179\u2013188"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB59","series-title":"Characteristics and Recognizability of Vocal Expressions of Emotions","author":"Van Bezooijen","year":"1984"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB60","first-page":"1369","article-title":"On determining the emotional state of pilots during flight: An exploratory study","volume":"40","author":"Williams","year":"1969","journal-title":"Aerospace Med."},{"key":"10.1016\/S0167-6393(03)00099-2_BIB61","series-title":"Speech Evaluation in Psychiatry","first-page":"189","article-title":"Vocal correlates of emotional states","author":"Williams","year":"1981"},{"key":"10.1016\/S0167-6393(03)00099-2_BIB62","doi-asserted-by":"crossref","unstructured":"Yamada, T., Hashimoto, H., Tosa, N., 1995. Pattern recognition of emotion with neural network. In: Proc. 1995 IEEE IECON 21st Internat. Conf. Industrial Electronics, Control, and Instrumentation, Vol. 1, pp. 183\u2013187","DOI":"10.1109\/IECON.1995.483355"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639303000992?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639303000992?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T21:42:06Z","timestamp":1585086126000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639303000992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,11]]},"references-count":62,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2003,11]]}},"alternative-id":["S0167639303000992"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(03)00099-2","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2003,11]]}}}