Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech Representations

1 code implementation • 14 Nov 2022 • Renee Lu, Mostafa Shahin, Beena Ahmed

We assess the performance of fine-tuning on both native and non-native children's speech, examine the effect of cross-domain child corpora, and investigate the minimum amount of child speech required to fine-tune a model which outperforms a state-of-the-art adult model.

Self-Supervised Learning speech-recognition +1