Measuring Acoustic Reduction in Feature Space

Modelling varying speaking style remains a challenge to state of the art speech recognition and synthesis systems. Vowel and consonant reduction have been identified as correlative to speaking style variation, but still lack a common measurement. The reduction phenomena are often observed without consideration of coarticulation and assimilation effects, and as a result of speaking rate variability. We present an analysis of acoustic reduction in Mel Frequency cepstral coefficients (MFCC) feature space of phonemes, estimate duration and determine the degree of correlation between duration reduction and feature space reduction for two different speaking styles present in broadcast news and conversational recordings. We analyse the feature space reduction of consonants and vowels in context in a syllable environment.