Broad Phonetic Class Definition driven by Phone Confusions
Eurasip Journal on Advances in Signal Processing Vol. 2012, Nº 158, pp. - - -, July, 2012.
ISSN (print): 1687-6172
Journal Impact Factor: 1,055 (in 2008)
Digital Object Identifier: 10.1186/1687-6180-2012-158
Download Full text PDF ( 1 MB)
Intermediate representations between the speech signal and phones may be used to improve discrimination among phones that are often confused. These representations are usually found according to broad phonetic classes, which are defined by a phonetician. This paper proposes an alternative data-driven method to generate these classes. Phone confusion information from the analysis of the output of a phone recognition system is used to find clusters at high risk of mutual confusion. A metric is defined to compute the distance between phones. The results, using TIMIT data, show that the proposed confusion-driven phone clustering method is an attractive alternative to the approaches based on human knowledge. A hierarchical classification structure to improve phone recognition is also proposed using a discriminative weight training method. Experiments show improvements in phone recognition on the TIMIT database compared to a baseline system.