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

2026-09-21

AI Summary

本文提出P2Flow，通过利用音素信息、渐进式架构设计和后训练声码器的方法解决极端条件下语音超分辨率性能下降的问题。

Abstract

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 information to reconstruct missing spectral components. Furthermore, it employs a progressive architectural design that hierarchically restores distinct frequency regions. Finally, we incorporate post-training of the vocoder to enhance overall waveform fidelity. Extensive experiments are conducted on the TIMIT and VCTK datasets under both 1 kHz to 16 kHz and 2 kHz to 16 kHz settings, demonstrating that P2Flow yields state-of-the-art results across multiple evaluation metrics.

Problem

• speech super-resolution
• extreme setting
• spectral inputs
• performance degradation

Innovation

• Phoneme-aware
• Progressive Flow Matching
• Extreme Speech Super-Resolution