Algoritmo de inserción de pausas para una lengua declinada

• Autores: Eva Navas Cordón , Iñaki Sainz Moncalvillo, Jon Sánchez de la Fuente, Ibon Saratxaga Couceiro , Inmaculada Hernáez Rioja
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 43, 2009, págs. 85-92
• Idioma: español
• Títulos paralelos:
  • Break insertion algoritm for an inflected language
• Enlaces
  • Texto completo
• Resumen
  • español

    Los sistemas de conversión de texto en habla necesitan un módulo para insertar las pausas que no vienen indicadas en el texto. En este trabajo se desarrolla un algoritmo de inserción de pausas para euskara estándar que utiliza información morfológica, sintáctica y del caso gramatical. El algoritmo se ha evaluado tanto objetiva como subjetivamente y los resultados confirman que este tipo de información es adecuada para realizar la predicción de las pausas en euskara estándar. Los tres tipos de información son relevantes y contribuyen a la mejora de los resultados del algoritmo.

  • English

    Text to speech synthesis systems must have a module to insert breaks that are not indicated in the text. In this paper an algorithm to insert breaks for standard Basque is developed. This algorithm uses morphology, syntax and information about the grammatical case. The algorithm has been evaluated both objectively and subjectively and the results confirm that this kind of information is suitable to make the prediction of the location of the breaks in standard Basque. All three types of information contribute to the improvements of the results of the algorithm.

• Referencias bibliográficas
  • Allen, J., D. Byron, M. Dzikovska, G. Aduriz I., Aranzabe M., Arriola J., Díaz de Ilarraza A., Gojenola K., Oronoz M., Uria L., 2004 A cascaded...
  • Allen, J., Hunnicut, S., Klatt, D. 1987. From text to speech: the MITalk system. Cambridge University Press, Cambridge.
  • Bachenko, J., Fitzpatrick, E., 1990 A Computational grammar of discourse-neutral prosodic parsing in English. Computational Linguistics, 16(3):...
  • Black, A.W.; Taylor, P., 1997. Assigning phrase breaks from part-of-speech sequences, en Proceedings of Eurospeech'97, páginas 995-998.
  • Boula de Mareüil, P., d’Alessandro, C., 1998. Text chunking for prosodic phrasing in French, en Proceedings of 3rd ESCA/COCOSDA International...
  • Bonafonte, A., Agüero, P.D. 2004. Phrase break prediction using a finite state transducer, en Proceedings de AST.
  • Carletta, J. 1996. Assessing agreement on classification task: the kappa statistic. Computational Linguistics, 22(2):249-254.
  • Castejón, F., Escalada, J.G., Monzón, L., Rodríguez, M.A., Sanz, P., 1994. Un conversor texto-voz para español. Comunicaciones de Telefónica...
  • Chen, C. J., 1999. Speech recognition with automatic punctuation, en Proceedings of Eurospeech, páginas 447-450.
  • Ezeiza N., Aduriz I., Alegria I., Arriola J.M., Urizar R., 1998. Combining stochastic and rule-based methods for disambiguation in agglutinative...
  • Frazier, L., Clifton, C., Carlson, K., 2004. Don't break, or do: prosodic boundary preferences. Lingua, 114(1): 3-27.
  • Hirschberg, J., Prieto, P., 1996. Training intonational phrasing rules automatically for English and Spanish text-to-speech. Speech Communication,...
  • Ingulfsen, T., Burrows, T., Buchholz, S., 2005. Influence of syntax on prosodic boundary prediction, en Proceedings of Interspeech, páginas...
  • Kim, J., Woodland, P. C., 2001. The use of prosody in a combined system for punctuation generation and speech recognition, en Proceedings...
  • Kim, S., Lee, J., Kim, B., Lee, G., 2006. Incorporating second-order information into two-step major phrase break prediction for Korean, en...
  • Koehn, P., Abney, S., Hirschberg, J., Collins, M., 2000. Improving intonational phrasing with syntactic information, en Proceedings of IEEE...
  • Liberman, M., Church, K., 1991. Text analysis and word pronunciation in text-to-speech synthesis, Advances in Speech Signal Processing, Dekker,...
  • Navas, E., Hernáez, I., Ezeiza, N., 2002. Assigning phrase breaks using CART's in Basque TTS, en Proceedings of Speech Prosody, páginas...
  • Ostendorf, M., Veilleux, N., 1994. A hierarchical stochastic model for automatic prediction of prosodic boundary location. Computational Linguistics,...
  • Read, I., Cox, S., 2004. Using part-of-speech for predicting phrase breaks, en Proceedings of Interspeech, páginas 741-744.
  • Sun, X., Applebaum, T.H., 2001. Intonational Phrase break prediction using decision tree and N-gram model, en Proceedings of Eurospeech, páginas...
  • Tesprasit, V., Charoenpornsawat, P., Sornlertlamvanich, V., 2003. Learning phrase break detection in Thai text-to- speech, en Proceedings...
  • Yoon, K., 2006. A prosodic phrasing model for a Korean text-to-speech synthesis system. Computer Speech & Language, 20(1): 69- 79.
  • Zervas, P., Xydas, G., Fakotakis, N., Kokkinakis, G., Kouroupetroglou, G., 2005. Experimental evaluation of tree-based algorithms for intonational...