Title :
Supervector pre-processing for PRSVM-based Chinese and Arabic dialect identification
Author :
Qian Zhang ; Boril, Hynek ; Hansen, John H. L.
Author_Institution :
Center for Robust Speech Syst. (CRSS), Univ. of Texas at Dallas, Richardson, TX, USA
Abstract :
Phonotactic modeling has become a widely used means for speaker, language, and dialect recognition. This paper explores variations to supervector pre-processing for phone recognition-support vector machines (PRSVM) based dialect identification. The aspects studied are: (i) normalization of supervector dimensions in the pre-squashing stage, (ii) impact of alternative squashing functions, and (iii) N-gram selection for supervector dimensionality reduction. In (i) and (ii), we find that several alternatives to commonly used approaches can provide moderate, yet consistent performance improvements. In (iii), a newly proposed dialect salience measure is applied in supervector dimension selection and compared to a common N-gram frequency based selection. The results show a strong correlation between dialect-salience and frequency of occurrence in N-grams. The evaluations in this study are conducted on a corpus of Chinese dialects, a Pan-Arabic corpus, and a set of Arabic CTS corpora.
Keywords :
natural language processing; speaker recognition; support vector machines; Arabic CTS corpora; Arabic dialect identification; Chinese dialect identification; N-gram selection; PRSVM; Pan-Arabic corpus; alternative squashing functions; dialect recognition; dialect salience measure; language recognition; phone recognition-support vector machines; phonotactic modeling; pre-squashing stage; speaker recognition; supervector dimension normalization; supervector pre-processing; Boolean functions; Data structures; Frequency estimation; Speech; Support vector machines; Training; Dialect identification; PRSVM; dialect-salience; phonotactic modeling; squashing function;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6639093