Análisis de las curvas melódicas del español en habla emotiva simulada

  1. Garrido Almiñana, Juan María
Aldizkaria:
Estudios de fonética experimental

ISSN: 2385-3573 1575-5533

Argitalpen urtea: 2011

Zenbakia: 20

Mota: Artikulua

Beste argitalpen batzuk: Estudios de fonética experimental

Laburpena

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.

Erreferentzia bibliografikoak

  • ADELL, J.; A. BONAFONTE y D. ESCUDERO (2005): «Analysis of prosodic features: towards modelling of emotional and pragmatic attributes of speech», Procesamiento 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=376A9A0BED1D5E6DE D7CDFD3880316F3.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/3356/3 257 [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», Proceedings 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.