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

Abstract

Abstract: 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 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?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance