2026
CONFIDENCE-BASED FILTERING FOR SPEECH DATASET CURATION WITH GENERATIVE SPEECH ENHANCEMENT USING DISCRETE TOKENS
ICASSP 2026poster
Generative speech enhancement (GSE) models show great promise in producing high-quality clean speech from noisy inputs, enabling applications such as curating noisy text-to-speech (TTS) datasets into high-quality ones. However, GSE models are prone to hallucination errors, such as phoneme omissions…