Analysis of melodic curves of Spanish in simulated emotional speech
Keywords:
melody, emotions, intonationAbstract
The goal of this work is to analyse acoustically the phonetic manifestation of the six basic emotions (anger, disgust, joy, fear, sadness, surprise) in the melodic curves of Spanish. 5.859 utterances, both neutral and emotional, taken from the Spanish INTERFACE corpus, were processed using MelAn, the tool for the automatic analysis of melodic curves described in Garrido (2010), to obtain data about the global (tonal range and height) and local (melodic patterns) behaviour of the melodic curves in a wide corpus of emotional speech. The obtained results confirm the conclusions of previous studies: the expression of emotion in Spanish is shown using changes in the tonal range and height, at global level, and rise-fall boundary patterns, at local level. The data of this work show, in addition, that the use of this melodic correlates is not general to all the analysed emotions, and that it seems to exist a relation between the degree of activation of emotions and the use of these correlates. They indicate also that declination slope can be an additional global parameter to distinguish neutral and emotional speech. Finally, the use of stress patterns specific of emotional speech has not been observed.
References
ADELL, J.; A. BONAFONTE y D. ESCUDERO (2005): «Analysis of prosodic features: towards modelling of emotional and pragmatic attributes of speech», Proce-samiento del Lenguaje Natural, 35, pp. 277-283.
BOERSMA, P. (2001): «Praat, a system for doing phonetics by computer», Glot International, 5-9/10, pp. 341-345.
COWIE, R. y R. R. CORNELIUS (2003): «Describing the emotional states that are expressed in speech», Speech Communication Special Issue on Speech an Emotion, 40, 1- 2, pp. 5-32.
EKMAN, P.; W. V. FRIESEN y P. ELLSWORTH (1982): «What emotion categories or dimensions can observers judge from facial behavior?» en P. Ekman (ed.): Emotion in the human face, Nueva York, Cambridge University Press, pp. 39-55.
FRANCISCO, V.; P. GERVÁS y R. HERVÁS (2005): «Analisis y síntesis de expresión emocional en cuentos leídos en voz alta», Procesamiento del Lenguaje Natural, 35, pp. 293-300.
GARRIDO, J. M. (1996): Modelling Spanish Intonation for Text-to-Speech Applications, tesis doctoral, Universitat Autònoma de Barcelona.
http://www.tdx.cat/handle/10803/4885;jsessionid=376A9A0BED1D5E6DED7CDFD3880316F3.tdx1 [08/08/2011].
GARRIDO, J. M. (2001): «La estructura de las curvas melódicas del español: propuesta de modelización», Lingüística Española Actual, XXIII, 2, pp. 173-209.
GARRIDO, J. M. (2010): «A Tool for Automatic F0 Stylisation, Annotation and Modelling of Large Corpora», Speech Prosody 2010, Chicago.
http://speechprosody2010.illinois.edu/papers/100041.pdf [14/1/2011].
HOZJAN, V.; Z. KACIC; A. MORENO; A. BONAFONTE y A. NOGUEIRAs (2002): «Interface databases: Design and collection of a multilingual emotional speech database», Proceedings of the Third Int. Conference on Language Resources and Evaluation (LREC'02), Las Palmas de Gran Canaria, pp. 2024-2028.
IRIONDO, I.; R. GUAUS; A. RODRÍGUEZ; P. LÁZARO; N. MONTOYA; J. M. BLANCO; D. BERNADAS; J. M. OLIVER; D. TENA y L. LONGHI (2000): «Validation of an acoustical modelling of emotional expression in Spanish using speech synthesis techniques», Proceedings of the ISCA Workshop on Speech and Emotion Northern Ireland, pp. 161–166.
MARTÍNEZ, H y D. ROJAS (2011): «Prosodia y emociones: datos acústicos, velocidad de habla y percepción de un corpus actuado», Lengua y habla, 15, pp. 59-72
http://erevistas.saber.ula.ve/index.php/lenguayhabla/article/viewFile/3356/3257 [14/11/2011].
MONTERO, J. M. (2003): Estrategias para la mejora de la naturalidad y la incorporación de variedad emocional a la conversión texto a voz en castellano, tesis doctoral, E.T.S.I. Telecomunicación (UPM).
MONTERO, J. M.; J. GUTIÉRREZ-ARRIOLA; J. COLÁS; E. ENRÍQUEZ y J. M. PARDO (1999): «Analysis and modelling of emotional speech in Spanish», Pro-ceedings of the 14th International Conference of Phonetic Sciences, San Francisco, USA, pp. 957–960.
NAVARRO, T. (1944): Manual de entonación española, Nueva York, Hispanic Institute on the United States.
RODRÍGUEZ, A.; P. LAZARO; N. MONTOYA; J. M. BLANCO; D. BERNADAS; J. M. OLIVER y L. LONGHI (1999): «Modelización acústica de la expresión emocional en el español», Procesamiento del Lenguaje Natural, 25, pp. 159-166.
SAINZ, I.; I. SARATXAGA; E. NAVAS; I. HERNÁEZ; J. SANCHEZ; I. LUENGO; I. ODRIOZOLA y E. DE BILBAO (2008): «Evaluación subjetiva de una base de datos emocional para euskera», V Jornadas en Tecnología del Habla, Bilbao.
http://jth2008.ehu.es/cd/pdfs/articulo/art_47.pdf [14/11/2011].
SCHRÖDER, M.; R. COWIE; E. DOUGLAS-COWIE; M. WESTERDIJK y S. GIELEN (2001): «Acoustic correlates of emotion dimensions in view of speech synthesis». Proceedings of Eurospeech 2001, Aalborg, Dinamarca, pp. 87–90.
WHISSEL, C. M. (1989): «The dictionary of affect in language», en R. Plutchik y H. Kellerman (eds): Emotion: Theory, Research and Experience, vol. 4: The Measurement of Emotions, Nueva York, Academic.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published online by Estudios de Fonética Experimental are licensed under Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND 4.0 DEED), unless otherwise noted. Estudios de Fonética Experimental is an open access journal. Estudios de Fonética Experimental is hosted by RCUB (Revistes Científiques de la Universitat de Barcelona), powered by Open Journal Systems (OJS) software. The copyright is not transferred to the journal: authors hold the copyright and publishing rights without restrictions. The author is free to use and distribute pre and post-prints versions of his/her article. However, preprint versions are regarded as a work-in-progress version used as internal communication with the authors, and we prefer to share postprint versions.
