论文信息 - Morphological segmentation for speech processing in Basque

Morphological segmentation for speech processing in Basque

Morphological information is traditionally used to develop high quality text to speech (TTS) and automatic speech recognition (ASR) systems. The use of this information improves the naturalness and intelligibility of the TTS synthesis and provides an appropriated way to select lexical units (LU) for ASR. Basque is an agglutinative language with a complex structure inside the words and the morphological information is essential both in TTS and ASR. In this work an automatic morphological segmentation tool oriented to TTS and ASR tasks is presented.

N. Ezeiza | M. Grana | K. Lopez de Ipina | G Bordel

[1] Eva Navas,et al. Assigning Phrase Breaks Using CARTs for Basque TTS , 2002 .

[2] Karmele López de Ipiña,et al. Using non-word lexical units in automatic speech understanding , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[3] Kepa Sarasola,et al. Automatic morphological analysis of Basque , 1996 .

[4] Inma Hernáez,et al. Description of the AhoTTS system for the Basque language , 2001, SSW.

[5] Manuel Graña,et al. Selection of Lexical Units for Continuous Speech Recognition of Basque , 2003, CIARP.

[6] Julia Hirschberg,et al. Training intonational phrasing rules automatically for English and Spanish text-to-speech , 1996, Speech Commun..

[7] Jean-Luc Gauvain,et al. Recent advances in transcribing television and radio broadcasts , 1999, EUROSPEECH.

[8] Toomas Altosaar,et al. Measuring the importance of morphological information for finnish speech synthesis , 2000, INTERSPEECH.

[9] Xabier Arregi,et al. XUXEN: A Spelling Checker/Corrector for Basque Based on Two-Level Morphology , 1992, ANLP.

[10] Katsuhiko Shirai,et al. Japanese large-vocabulary continuous-speech recognition using a newspaper corpus and broadcast news , 1999, Speech Commun..