# How does end-to-end speech recognition training impact speech enhancement artifacts?

arXiv: https://arxiv.org/abs/2311.11599 · HTML: https://mlsanity.com/paper/2311.11599/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2023.

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

- [Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition](https://mlsanity.com/paper/2409.00815/) (2024)
- [Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement](https://mlsanity.com/paper/2508.20859/) (2025)
- [VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification](https://mlsanity.com/paper/2502.07205/) (2025)
- [Revealing the Role of Audio Channels in ASR Performance Degradation](https://mlsanity.com/paper/2508.08967/) (2025)
- [Alternating Approach-Putt Models for Multi-Stage Speech Enhancement](https://mlsanity.com/paper/2508.10436/) (2025)
- [Training-Free Intelligibility-Guided Observation Addition for Noisy ASR](https://mlsanity.com/paper/2602.20967/) (2026)

## Abstract (arXiv)

Jointly training a speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end has been investigated as a way to mitigate the influence of processing distortion generated by single-channel SE on ASR. In this paper, we investigate the effect of such joint training on the signal-level characteristics of the enhanced signals from the viewpoint of the decomposed noise and artifact errors. The experimental analyses provide two novel findings: 1) ASR-level training of the SE front-end reduces the artifact errors while increasing the noise errors, and 2) simply interpolating the enhanced and observed signals, which achieves a similar effect of reducing artifacts and increasing noise, improves ASR performance without jointly modifying the SE and ASR modules, even for a strong ASR back-end using a WavLM feature extractor. Our findings provide a better understanding of the effect of joint training and a novel insight for designing an ASR agnostic SE front-end.