# Investigating training objective for flow matching-based speech enhancement

arXiv: https://arxiv.org/abs/2512.10382 · HTML: https://mlsanity.com/paper/2512.10382/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation](https://mlsanity.com/paper/2303.00848/) (2023)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019)
- [Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement](https://mlsanity.com/paper/2302.14748/) (2023)
- [Schr"odinger Bridge for Generative Speech Enhancement](https://mlsanity.com/paper/2407.16074/) (2024)
- [FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancement](https://mlsanity.com/paper/2206.07293/) (2022)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [FlowSE: Flow Matching-based Speech Enhancement](https://mlsanity.com/paper/2508.06840/) (2025)
- [Investigating Training Objectives for Generative Speech Enhancement](https://mlsanity.com/paper/2409.10753/) (2024)
- [FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching](https://mlsanity.com/paper/2505.19476/) (2025)
- [The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement](https://mlsanity.com/paper/2406.03460/) (2024)
- [Multi-Metric Preference Alignment for Generative Speech Restoration](https://mlsanity.com/paper/2508.17229/) (2025)

## Built on by (most cited first, 1 of 1)

- [Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy](https://mlsanity.com/paper/2602.00568/) (2026)

## Abstract (arXiv)

Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching offers a more efficient alternative by directly learning a velocity field that maps noise to data. In this work, we present a systematic study of flow matching for SE under three training objectives: velocity prediction, x1 prediction, and preconditioned x1 prediction. We analyze their impact on training dynamics and overall performance. Moreover, by introducing perceptual(PESQ) and signal-based(SI-SDR) objectives, we further enhance convergence efficiency and speech quality, yielding substantial improvements across evaluation metrics.