# Where Speech Enhancement Hurts Recognition: An Inference Time Polar Projection Diagnosis

arXiv: https://arxiv.org/abs/2607.11157 · HTML: https://mlsanity.com/paper/2607.11157/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 28 of 28)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [A Wavenet for Speech Denoising](https://mlsanity.com/paper/1706.07162/) (2017)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancement](https://mlsanity.com/paper/2206.07293/) (2022)
- [MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation](https://mlsanity.com/paper/2312.11825/) (2023)
- [On The Compensation Between Magnitude and Phase in Speech Separation](https://mlsanity.com/paper/2108.05470/) (2021)
- [Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2110.05267/) (2021)
- [Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition](https://mlsanity.com/paper/2201.03881/) (2022)
- [FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching](https://mlsanity.com/paper/2505.19476/) (2025)
- [Dual Application of Speech Enhancement for Automatic Speech Recognition](https://mlsanity.com/paper/2011.03840/) (2020)
- [ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment](https://mlsanity.com/paper/2506.19398/) (2025)
- [Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition](https://mlsanity.com/paper/2106.00949/) (2021)
- [End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction](https://mlsanity.com/paper/1804.10204/) (2018)
- [Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance](https://mlsanity.com/paper/2404.14860/) (2024)
- [SNRi Target Training for Joint Speech Enhancement and Recognition](https://mlsanity.com/paper/2111.00764/) (2021)
- [Effect of noise suppression losses on speech distortion and ASR performance](https://mlsanity.com/paper/2111.11606/) (2021)
- [How does end-to-end speech recognition training impact speech enhancement artifacts?](https://mlsanity.com/paper/2311.11599/) (2023)
- [MeanFlowSE: one-step generative speech enhancement via conditional mean flow](https://mlsanity.com/paper/2509.14858/) (2025)
- [Too Good to Be True: A Study on Modern Automatic Speech Recognition for the Evaluation of Speech Enhancement](https://mlsanity.com/paper/2605.12107/) (2026)
- [Task-aware Warping Factors in Mask-based Speech Enhancement](https://mlsanity.com/paper/2108.12128/) (2021)
- [Mask scalar prediction for improving robust automatic speech recognition](https://mlsanity.com/paper/2204.12092/) (2022)
- [When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems](https://mlsanity.com/paper/2512.17562/) (2025)
- [Training-Free Intelligibility-Guided Observation Addition for Noisy ASR](https://mlsanity.com/paper/2602.20967/) (2026)

## Abstract (arXiv)

Speech enhancement (SE) can substantially improve perceptual quality, yet enhanced speech does not necessarily improve automatic speech recognition (ASR). Common explanations such as enhancement artifacts and over-suppression remain qualitative and do not localize which enhancement component affects recognition. We study inference-time polar projection, which transforms an STFT mask M=Aejφ into Mα,γ=Aα ejγφ and independently varies magnitude strength and estimated phase correction with frozen SE and ASR models. The resulting response curves separate effects that are coupled in ordinary enhanced-vs-noisy comparisons. On VoiceBank+DEMAND with FRCRN, wav2vec2.0 improves from 17.13 to 10.20 WER near full magnitude correction (α=.85), while Whisper reaches its best WER under much weaker correction, improving from 6.44 to 5.57 at α=.25 and returning to 6.46 at full magnitude. A second enhancer, a robustness-oriented ASR model, and a reverberant WSJ0 mixture set generalize the pattern and show that the preferred magnitude region depends on the recognizer and acoustic condition. Estimated phase correction is not a stable ASR lever in these evaluations: its effect is smaller, setting-dependent, and provides no consistent gain once magnitude strength is fixed.