Phonemic variability and confusability in pronunciation modeling for automatic speech recognition

Autor: Karanasou, Panagiota

Cette thèse aborde les problèmes de variabilité et confusabilité phonémique du point de vue des modèles de prononciation pour un système de reconnaissance automatique de la parole. En particulier, plusieurs directions de recherche sont étudi�

Externí odkaz: http://www.theses.fr/2013PA112087/document

Measuring the Confusability of Pronunciations in Speech Recognition

Autor: Karanasou, Panagiota, Yvon, François, Lamel, Lori

Publikováno v: International Workshop on Finite State Methods and Natural Language Processing
International Workshop on Finite State Methods and Natural Language Processing, Jan 2011, Tours, France

International audience; In this work, we define a measure aimed at assessing how well a pronunciation model will function when used as a component of a speech recognition system. This measure, {\\it pronunciation entropy}, fuses information from both

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::aacd04f4914d836ec7f810eae09af87f
https://hal.archives-ouvertes.fr/hal-01960733

Comparing SMT Methods for Automatic Generation of Pronunciation Variants.

Autor: Karanasou, Panagiota, Lamel, Lori

Publikováno v: Advances in Natural Language Processing: 7th International Conference on Nlp, Icetal 2010, Reykjavik, Iceland, August 16-18, 2010; 2010, p167-178, 12p