# Effect of noise suppression losses on speech distortion and ASR performance

arXiv: https://arxiv.org/abs/2111.11606 · HTML: https://mlsanity.com/paper/2111.11606/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2021.

## Built on by (most cited first, 4 of 4)

- [AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement](https://mlsanity.com/paper/2501.15417/) (2025)
- [Towards Real-Time Generative Speech Restoration with Flow-Matching](https://mlsanity.com/paper/2510.16997/) (2025)
- [Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data](https://mlsanity.com/paper/2405.19497/) (2024)
- [When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems](https://mlsanity.com/paper/2512.17562/) (2025)

## Abstract (arXiv)

Deep learning based speech enhancement has made rapid development towards improving quality, while models are becoming more compact and usable for real-time on-the-edge inference. However, the speech quality scales directly with the model size, and small models are often still unable to achieve sufficient quality. Furthermore, the introduced speech distortion and artifacts greatly harm speech quality and intelligibility, and often significantly degrade automatic speech recognition (ASR) rates. In this work, we shed light on the success of the spectral complex compressed mean squared error (MSE) loss, and how its magnitude and phase-aware terms are related to the speech distortion vs. noise reduction trade off. We further investigate integrating pre-trained reference-less predictors for mean opinion score (MOS) and word error rate (WER), and pre-trained embeddings on ASR and sound event detection. Our analyses reveal that none of the pre-trained networks added significant performance over the strong spectral loss.