 |
Speech Recognition and Intrinsic Variation (SRIV2006)Toulouse, France |
 |
|
Speech Recognition and Intrinsic Variation (SRIV2006)Toulouse, France |
|
This paper proposes a method for the measurement and quantification of the impact of accents on speech models. An accent metric is introduced based on the cross entropy (CE) of the probability models of speech from different accents. The CE metric has potentials for use in analysis, identification, quantification and ranking of the salient features of accents. The accent metric is used for phonetic-tree cluster analysis of phonemes, for cross-accent phonetic clustering and for quantification of the distances of phonetic sounds in different English accents. Experimental evaluation presented quantifies the effect of American, British and Australian accents on acoustic realisation of phonemes.
Full Paper
Presentation (.ppt)
Bibliographic reference. Ghorshi, Seyed Alireza / Vaseghi, Saeed / Yan, Qin (2006): "Cross entropy information metric for quantification and cluster analysis of accents", In SRIV-2006, 119-122.