ISCA Archive SLTU 2014
ISCA Archive SLTU 2014

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

Anjana Vakil, Alexis Palmer

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.

Index Terms: under-resourced languages, speech recognition, lexicon building, phoneme mapping


Cite as: Vakil, A., Palmer, A. (2014) Cross-language mapping for small-vocabulary ASR in under-resourced languages: investigating the impact of source language choice. Proc. 4th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2014), 169-175

@inproceedings{vakil14_sltu,
  author={Anjana Vakil and Alexis Palmer},
  title={{Cross-language mapping for small-vocabulary ASR in under-resourced languages: investigating the impact of source language choice}},
  year=2014,
  booktitle={Proc. 4th Workshop on Spoken Language Technologies for Under-Resourced Languages  (SLTU 2014)},
  pages={169--175}
}