# Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration

arXiv: https://arxiv.org/abs/2211.02397 · HTML: https://mlsanity.com/paper/2211.02397/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 4 Nov 2022.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [Universal Speech Enhancement with Score-based Diffusion](https://mlsanity.com/paper/2206.03065/) (2022)
- [A Study on Speech Enhancement Based on Diffusion Probabilistic Model](https://mlsanity.com/paper/2107.11876/) (2021)
- [NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling](https://mlsanity.com/paper/2104.02321/) (2021)
- [VoiceFixer: Toward General Speech Restoration with Neural Vocoder](https://mlsanity.com/paper/2109.13731/) (2021)
- [HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement](https://mlsanity.com/paper/2203.13086/) (2022)
- [Neural Vocoder is All You Need for Speech Super-resolution](https://mlsanity.com/paper/2203.14941/) (2022)
- [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)
- [Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder](https://mlsanity.com/paper/2102.08706/) (2021)
- [Speech Dereverberation Using Fully Convolutional Networks](https://mlsanity.com/paper/1803.08243/) (2018)
- [TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining](https://mlsanity.com/paper/2110.13492/) (2021)

## Built on by (most cited first, 30 of 34)

- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [FlowSE: Flow Matching-based Speech Enhancement](https://mlsanity.com/paper/2508.06840/) (2025)
- [LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement](https://mlsanity.com/paper/2503.00493/) (2025)
- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [Single and Few-step Diffusion for Generative Speech Enhancement](https://mlsanity.com/paper/2309.09677/) (2023)
- [FlowDec: A flow-based full-band general audio codec with high perceptual quality](https://mlsanity.com/paper/2503.01485/) (2025)
- [The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement](https://mlsanity.com/paper/2406.03460/) (2024)
- [Investigating the Design Space of Diffusion Models for Speech Enhancement](https://mlsanity.com/paper/2312.04370/) (2023)
- [DDTSE: Discriminative Diffusion Model for Target Speech Extraction](https://mlsanity.com/paper/2309.13874/) (2023)
- [Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler](https://mlsanity.com/paper/2312.02683/) (2023)
- [High-Resolution Speech Restoration with Latent Diffusion Model](https://mlsanity.com/paper/2409.11145/) (2024)
- [Multi-Metric Preference Alignment for Generative Speech Restoration](https://mlsanity.com/paper/2508.17229/) (2025)
- [On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings](https://mlsanity.com/paper/2306.03014/) (2023)
- [Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge](https://mlsanity.com/paper/2406.06139/) (2024)
- [FlowTSE: Target Speaker Extraction with Flow Matching](https://mlsanity.com/paper/2505.14465/) (2025)
- [DiffSED: Sound Event Detection with Denoising Diffusion](https://mlsanity.com/paper/2308.07293/) (2023)
- [VoiceBridge: General Speech Restoration with One-step Latent Bridge Models](https://mlsanity.com/paper/2509.25275/) (2025)
- [Towards Real-Time Generative Speech Restoration with Flow-Matching](https://mlsanity.com/paper/2510.16997/) (2025)
- [Real-Time Streamable Generative Speech Restoration with Flow Matching](https://mlsanity.com/paper/2512.19442/) (2025)
- [The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems](https://mlsanity.com/paper/2406.06160/) (2024)
- [Adaptive Deterministic Flow Matching for Target Speaker Extraction](https://mlsanity.com/paper/2510.16995/) (2025)
- [Speech Signal Improvement Using Causal Generative Diffusion Models](https://mlsanity.com/paper/2303.08674/) (2023)
- [A Hybrid Model for Weakly-Supervised Speech Dereverberation](https://mlsanity.com/paper/2502.06839/) (2025)
- [Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech](https://mlsanity.com/paper/2410.17834/) (2024)
- [Regularized Schr"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement](https://mlsanity.com/paper/2511.11686/) (2025)
- [A Dual-Branch Parallel Network for Speech Enhancement and Restoration](https://mlsanity.com/paper/2409.08702/) (2024)
- [Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement](https://mlsanity.com/paper/2409.09642/) (2024)
- [Speech Enhancement based on cascaded two flows](https://mlsanity.com/paper/2508.06842/) (2025)

## Abstract (arXiv)

Diffusion-based generative models have had a high impact on the computer vision and speech processing communities these past years. Besides data generation tasks, they have also been employed for data restoration tasks like speech enhancement and dereverberation. While discriminative models have traditionally been argued to be more powerful e.g. for speech enhancement, generative diffusion approaches have recently been shown to narrow this performance gap considerably. In this paper, we systematically compare the performance of generative diffusion models and discriminative approaches on different speech restoration tasks. For this, we extend our prior contributions on diffusion-based speech enhancement in the complex time-frequency domain to the task of bandwith extension. We then compare it to a discriminatively trained neural network with the same network architecture on three restoration tasks, namely speech denoising, dereverberation and bandwidth extension. We observe that the generative approach performs globally better than its discriminative counterpart on all tasks, with the strongest benefit for non-additive distortion models, like in dereverberation and bandwidth extension. Code and audio examples can be found online at https://uhh.de/inf-sp-sgmsemultitask