13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Computational Modelling of the Recognition of Foreign-Accented Speech

Odette Scharenborg (1,2), Marijt Witteman (1,3), Andrea Weber (1,2)

(1) Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands
(2) Donders Institute for Brain, Cognition and Behaviour, Radboud University Nijmegen, the Netherlands
(3) Radboud University Nijmegen, The Netherlands

In foreign-accented speech, pronunciation typically deviates from the canonical form to some degree. For native listeners, it has been shown that word recognition is more difficult for strongly-accented words than for less strongly-accented words. Furthermore recognition of strongly-accented words becomes easier with additional exposure to the foreign accent. In this paper, listeners' behaviour was simulated with Fine-tracker, a computational model of word recognition that uses real speech as input. The simulations showed that, in line with human listeners, 1) Fine-Tracker's recognition outcome is modulated by the degree of accentedness and 2) it improves slightly after brief exposure with the accent. On the level of individual words, however, Fine-tracker failed to correctly simulate listeners' behaviour, possibly due to differences in overall familiarity with the chosen accent (German-accented Dutch) between human listeners and Fine-Tracker.

Index Terms: foreign-accented speech, accent strength, word recognition, computational modelling, German-accented Dutch

Full Paper

Bibliographic reference.  Scharenborg, Odette / Witteman, Marijt / Weber, Andrea (2012): "Computational modelling of the recognition of foreign-accented speech", In INTERSPEECH-2012, 883-886.