Can Layer-Wise SSL Features Improve Zero-Shot ASR Performance for Children’s Speech?

Automatic Speech Recognition (ASR) systems often struggle to accurately process children’s speech dueto its distinct and highly variable acoustic and linguistic characteristics. While recent advancements in self-supervised learning (SSL) models have greatly enhanced the transcription of adult speech, accurately transcribing children’s speech remains a significant challenge. This study investigates the effectiveness of layer-wise features extracted from state-of-the-art SSL pre-trained models – specifically, Wav2Vec2, HuBERT, Data2Vec, and WavLM in improving the performance of ASR for children’s speech in zero-shot scenarios.