Variability and stability in native and non-native Japanese speech

Abstract

The speech of second language learners is often characterized as more variable than the speech of native speakers (e.g., Baese-Berk and Morrill, 2015; Jongman and Wade, 2007; Jongman et al., 2007; Rogerset al., 2012). However, among the relatively few studies which have examined this question directly, the majority have focused on: learners of English, learners from one L1 background, and have examined one linguistic feature per study, leaving open the possibility that non-native speech may not be more variable than native speech in all cases. The present work examines the production of Japanese sentences by native Japanese speakers, and learners of Japanese from two language backgrounds (English and Chinese). Counter to previous results, we find several cases where non-native speakers are less variable than native speakers, including on various measures of vowel spectrum variability, and voiced stop realization. Thus, the relationship between variability and language background appears to be more complex than previously thought. Accurately characterizing variability across native and non-native speech has implications for models of second language acquisition, and speech perception. We suggest that future work on variability in non-native speech should examine factors such as speakers’ L1 and L2, and multiple linguistic features.