Generation of Phonetic Units for Mixed-Language Speech Recognition Based on Acoustic and Contextual Analysis

@article{citeulike:2939469, abstract = {This work presents a novel approach to generating phonetic units in order to recognize mixed-language or multilingual speech. Acoustic and contextual analysis is performed to characterize multilingual phonetic units for phone set creation. Acoustic likelihood is utilized for similarity estimation of phone models. The hyperspace analog to language (HAL) model is adopted for contextual modeling and contextual similarity estimation. A confusion matrix combining acoustic and contextual similarities between every two phonetic units is built for phonetic unit clustering. Multidimensional scaling (MDS) method is applied to the confusion matrix for reducing dimensionality. Experimental results indicate that the created phonetic set provides a compact and robust set that considers acoustic and contextual information for mixed-language or multilingual speech recognition.}, author = {Huang, Chien-Lin and Wu, Chung-Hsien }, booktitle = {Computers, IEEE Transactions on}, citeulike-article-id = {2939469}, doi = {http://dx.doi.org/10.1109/TC.2007.1064}, journal = {Computers, IEEE Transactions on}, keywords = {textmining}, number = {9}, pages = {1225--1233}, posted-at = {2008-06-28 18:17:17}, priority = {2}, title = {Generation of Phonetic Units for Mixed-Language Speech Recognition Based on Acoustic and Contextual Analysis}, url = {http://dx.doi.org/10.1109/TC.2007.1064}, volume = {56}, year = {2007} }

TY - JOUR ID - citeulike:2939469 L3 - citeulike-article-id:2939469 N2 - This work presents a novel approach to generating phonetic units in order to recognize mixed-language or multilingual speech. Acoustic and contextual analysis is performed to characterize multilingual phonetic units for phone set creation. Acoustic likelihood is utilized for similarity estimation of phone models. The hyperspace analog to language (HAL) model is adopted for contextual modeling and contextual similarity estimation. A confusion matrix combining acoustic and contextual similarities between every two phonetic units is built for phonetic unit clustering. Multidimensional scaling (MDS) method is applied to the confusion matrix for reducing dimensionality. Experimental results indicate that the created phonetic set provides a compact and robust set that considers acoustic and contextual information for mixed-language or multilingual speech recognition. IS - 9 JF - Computers, IEEE Transactions on EP - 1233 TI - Generation of Phonetic Units for Mixed-Language Speech Recognition Based on Acoustic and Contextual Analysis VL - 56 T2 - Computers, IEEE Transactions on SP - 1225 KW - textmining AU - Huang, Chien-Lin AU - Wu, Chung-Hsien PY - 2007/// UR - http://dx.doi.org/10.1109/TC.2007.1064 ER -