SOURCE-LINKED INTELLIGENCE

P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has concentrated on standard or versatile SSR configurations, leaving the extreme setting with severely limited spectral inputs largely unexplored. In this regime, current approaches exhibit marked performance degradation, underscoring the need for dedicated solutions. To bridge this gap, we introduce P2Flow, a phoneme-aware progressive flow matching (FM) framework designed for extreme SSR with three main strategies. First, our model leverages phonetic

Read original source ↗ Open in workspace

recordType

paper

region

Global