Cross-language mapping for small-vocabulary ASR in under-resourced languages: investigating the impact of source language choice

For small-vocabulary applications, a mapped pronunciation lexicon can enable speech recognition in a target underresourced language using an out-of-the-box recognition engine for a high-resource source language. Existing algorithms for cross-language phoneme mapping enable the fully automatic creation of such lexicons using just a few minutes of audio, making speech-driven applications in any language feasible. What such methods have not considered is whether careful selection of the source language based on the linguistic properties of the target language can improve recognition accuracy; this paper reports on a preliminary exploration of this question. Results from a first case study seem to indicate that phonetic similarity between target and source language does not significantly impact accuracy, underscoring the languageindependence of such techniques.