Discrete Audio Tokens Enhance Data Efficiency in Low-Resource Speech Model Fine-Tuning

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: Does replacing mel-spectrograms with discrete audio tokens improve data efficiency and convergence speed when fine-tuning self-supervised speech models on languages with under 10 hours of labeled data. 12 claims were extracted from source literature; 12 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Does replacing mel-spectrograms with discrete audio tokens improve data efficiency and convergence speed when fine-tuning self-supervised speech models on languages with under 10 hours of labeled data?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.