A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
Chou, Cheng-Kang, Hsu, Chan-Jan, Chung, Ho-Lam, Tseng, Liang-Hsuan, Cheng, Hsi-Chun, Fu, Yu-Kuan, Huang, Kuan Po, Lee, Hung-Yi
–arXiv.org Artificial Intelligence
We propose a self-refining framework that enhances ASR performance with only unlabeled datasets. The process starts with an existing ASR model generating pseudo-labels on unannotated speech, which are then used to train a high-fidelity text-to-speech (TTS) system. Then, synthesized speech text pairs are bootstrapped into the original ASR system, completing the closed-loop self-improvement cycle. We demonstrated the effectiveness of the framework on Taiwanese Mandarin speech. Leveraging 6,000 hours of unlabeled speech, a moderate amount of text data, and synthetic content from the AI models, we adapt Whisper-large-v2 into a specialized model, Twister. Twister reduces error rates by up to 20% on Mandarin and 50% on Mandarin-English code-switching benchmarks compared to Whisper. Results highlight the framework as a compelling alternative to pseudo-labeling self-distillation approaches and provides a practical pathway for improving ASR performance in low-resource or domain-specific settings.
arXiv.org Artificial Intelligence
Jun-17-2025
- Genre:
- Research Report (1.00)
- Industry:
- Education > Educational Setting > Online (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Speech > Speech Recognition (1.00)
- Natural Language (1.00)
- Machine Learning (1.00)
- Information Technology > Artificial Intelligence