Impact of Masking Ratio on Discrete Speech Unit Correction Accuracy for Accent Adaptation

Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete acoustic units. We propose to correct the discovered discrete units for accented speech back to a standard pronunciation in an unsupervised manner. A masked language model is trained on discrete units from a standard accent and iteratively corrects an accented token sequence by masking unexpected cluster sequences and predicting their common variant. Small acc

Research goal: What is the impact of varying the masking ratio in the masked language model on the correction accuracy of discrete speech units for accent adaptation, measured by the reduction in WER on noisy speech datasets?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.