DocumentCode
2256731
Title
Evaluation of the Telefonica I+D Natural Numbers Recognizer over different dialects of Spanish from Spain and America
Author
De La Torre, C. ; Caminero-Gil, F.J. ; Alvarez, J. ; Del Álamo, C. Martín ; Hernández-Gómez, L.
Author_Institution
Speech Technol. Group, Telefonica Investigacion y Desarrollo, Madrid, Spain
Volume
4
fYear
1996
fDate
3-6 Oct 1996
Firstpage
2032
Abstract
Presents the results obtained when evaluating the Natural Numbers Recognizer of Telefonica Investigacion y Desarrollo (I+D) over some particular dialects of Spanish from Spain and America. The evaluation was made over two different data sets, corresponding to two different situations. The first set includes dialects of Spanish from Spain that were considered in the training and design of our baseline system, and the second set corresponds to Argentinian Spanish, which was not considered in the training of the original system. Because we are interested in a system that can be used by a wide range of users, we tested the possibilities of MAP (maximum a-priori) techniques to adapt the original HMMs in order to represent all the dialects. The experimental results show the capabilities of our recognizer for use in applications spread over a great number of Spanish-speaking countries
Keywords
hidden Markov models; languages; linguistics; maximum likelihood estimation; speech recognition; America; Argentina; Natural Numbers Recognizer; Spain; Spanish dialects; Spanish-speaking countries; Telefonica Investigacion y Desarrollo; baseline system training; data sets; hidden Markov models; maximum a-priori techniques; Cepstrum; Hidden Markov models; Merging; Natural languages; Speech analysis; Speech recognition; System testing; Telecommunications; Telephony; Vocabulary;
fLanguage
English
Publisher
ieee
Conference_Titel
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location
Philadelphia, PA
Print_ISBN
0-7803-3555-4
Type
conf
DOI
10.1109/ICSLP.1996.607198
Filename
607198
Link To Document