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

arXiv: https://arxiv.org/abs/2609.24138 · HTML: https://mlsanity.com/paper/2609.24138/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Denoising Diffusion Bridge Models](https://mlsanity.com/paper/2309.16948/) (2023)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech](https://mlsanity.com/paper/2005.05106/) (2020)
- [NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling](https://mlsanity.com/paper/2104.02321/) (2021)
- [A Fully Progressive Approach to Single-Image Super-Resolution](https://mlsanity.com/paper/1804.02900/) (2018)
- [AudioSR: Versatile Audio Super-resolution at Scale](https://mlsanity.com/paper/2309.07314/) (2023)
- [Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations](https://mlsanity.com/paper/1909.06628/) (2019)
- [NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates](https://mlsanity.com/paper/2206.08545/) (2022)
- [Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution](https://mlsanity.com/paper/2210.15793/) (2022)
- [FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching](https://mlsanity.com/paper/2501.04926/) (2025)
- [AERO: Audio Super Resolution in the Spectral Domain](https://mlsanity.com/paper/2211.12232/) (2022)
- [Audio Super-Resolution with Latent Bridge Models](https://mlsanity.com/paper/2509.17609/) (2025)
- [Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction](https://mlsanity.com/paper/2401.06387/) (2024)
- [Bridge-SR: Schr"odinger Bridge for Efficient SR](https://mlsanity.com/paper/2501.07897/) (2025)
- [A2SB: Audio-to-Audio Schrodinger Bridges](https://mlsanity.com/paper/2501.11311/) (2025)
- [Self-Attention for Audio Super-Resolution](https://mlsanity.com/paper/2108.11637/) (2021)
- [Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolution](https://mlsanity.com/paper/2409.09337/) (2024)
- [TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining](https://mlsanity.com/paper/2110.13492/) (2021)
- [Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach](https://mlsanity.com/paper/2410.00025/) (2024)
- [A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models](https://mlsanity.com/paper/2605.16681/) (2026)
- [EBEN: Extreme bandwidth extension network applied to speech signals captured with noise-resilient body-conduction microphones](https://mlsanity.com/paper/2210.14090/) (2022)
- [Vector Quantized Diffusion Model Based Speech Bandwidth Extension](https://mlsanity.com/paper/2409.05784/) (2024)
- [SAGA-SR: Semantically and Acoustically Guided Audio Super-Resolution](https://mlsanity.com/paper/2509.24924/) (2025)
- [Towards Real-Time Generative Speech Restoration with Flow-Matching](https://mlsanity.com/paper/2510.16997/) (2025)

## Abstract (arXiv)

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.