Evaluating intra- and crosslingual adaptation for non-native speech recognition in a bilingual environment

In this paper, use of intra- and crosslingual adaptation is addressed in cognitive infocommunication, for an ASR application in a bilingual environment. State-of-the-art linear regression based adaptation approaches are evaluated after a brief theoretical overview of the applied techniques. As expected, these contribute to significant improvement when used for intralingual adaptation. A simple phoneme mapping based approach is investigated for crosslingual adaptation between French and German in order to evaluate whether non-native data can help speech recognition. It is found that using native data for adapting a speech recognizer operating in the non-native language of the speaker, a modest improvement can be reached. However, when adaptation data is available from the speaker in its non-native language, it remains a better source of adaptation.