Automatic Speech Recognition of Non-Native Child Speech for Language Learning Applications
This addresses the challenge of developing voicebots for non-native child language learners, though it is incremental as it applies existing methods to a new data type.
The study evaluated Wav2Vec2.0 and Whisper AI ASR systems on native and non-native Dutch children's speech, finding that pre-trained transformer models achieve acceptable performance for extracting detailed phoneme pronunciation feedback.
Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning. Voicebots, though, have largely been geared towards native adult speakers. We sought to assess the performance of two state-of-the-art ASR systems, Wav2Vec2.0 and Whisper AI, with a view to developing a voicebot that can support children acquiring a foreign language. We evaluated their performance on read and extemporaneous speech of native and non-native Dutch children. We also investigated the utility of using ASR technology to provide insight into the children's pronunciation and fluency. The results show that recent, pre-trained ASR transformer-based models achieve acceptable performance from which detailed feedback on phoneme pronunciation quality can be extracted, despite the challenging nature of child and non-native speech.