# On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings

arXiv: https://arxiv.org/abs/2306.03014 · HTML: https://mlsanity.com/paper/2306.03014/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [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)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement](https://mlsanity.com/paper/2203.13086/) (2022)
- [Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration](https://mlsanity.com/paper/2211.02397/) (2022)
- [Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder](https://mlsanity.com/paper/2102.08706/) (2021)
- [Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling](https://mlsanity.com/paper/1903.04567/) (2019)
- [Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier](https://mlsanity.com/paper/2102.06454/) (2021)
- [Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes](https://mlsanity.com/paper/2206.11703/) (2022)

## Built on by (most cited first, 6 of 6)

- [High-Resolution Speech Restoration with Latent Diffusion Model](https://mlsanity.com/paper/2409.11145/) (2024)
- [ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancement](https://mlsanity.com/paper/2509.19495/) (2025)
- [Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech](https://mlsanity.com/paper/2410.17834/) (2024)
- [Are Deep Speech Denoising Models Robust to Adversarial Noise?](https://mlsanity.com/paper/2503.11627/) (2025)
- [Predictive-Generative Drift Decomposition for Speech Enhancement and Separation](https://mlsanity.com/paper/2605.06189/) (2026)
- [Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers](https://mlsanity.com/paper/2608.30329/) (2026)

## Abstract (arXiv)

Since its inception, the field of deep speech enhancement has been dominated by predictive (discriminative) approaches, such as spectral mapping or masking. Recently, however, novel generative approaches have been applied to speech enhancement, attaining good denoising performance with high subjective quality scores. At the same time, advances in deep learning also allowed for the creation of neural network-based metrics, which have desirable traits such as being able to work without a reference (non-intrusively). Since generatively enhanced speech tends to exhibit radically different residual distortions, its evaluation using instrumental speech metrics may behave differently compared to predictively enhanced speech. In this paper, we evaluate the performance of the same speech enhancement backbone trained under predictive and generative paradigms on a variety of metrics and show that intrusive and non-intrusive measures correlate differently for each paradigm. This analysis motivates the search for metrics that can together paint a complete and unbiased picture of speech enhancement performance, irrespective of the model's training process.