# Improving noise robust automatic speech recognition with single-channel time-domain enhancement network

arXiv: https://arxiv.org/abs/2003.03998 · HTML: https://mlsanity.com/paper/2003.03998/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2020.

## Built on by (most cited first, 21 of 21)

- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition](https://mlsanity.com/paper/2110.04934/) (2021)
- [Measuring the Accuracy of Automatic Speech Recognition Solutions](https://mlsanity.com/paper/2408.16287/) (2024)
- [Investigating the Design Space of Diffusion Models for Speech Enhancement](https://mlsanity.com/paper/2312.04370/) (2023)
- [Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancement](https://mlsanity.com/paper/2406.13471/) (2024)
- [Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments](https://mlsanity.com/paper/2309.06183/) (2023)
- [Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection](https://mlsanity.com/paper/2310.08869/) (2023)
- [Audio-Visual Speech Separation Using Cross-Modal Correspondence Loss](https://mlsanity.com/paper/2103.01463/) (2021)
- [Time-domain Speech Enhancement with Generative Adversarial Learning](https://mlsanity.com/paper/2103.16149/) (2021)
- [Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance](https://mlsanity.com/paper/2408.06264/) (2024)
- [CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR](https://mlsanity.com/paper/2502.20040/) (2025)
- [Chain-based Discriminative Autoencoders for Speech Recognition](https://mlsanity.com/paper/2203.13687/) (2022)
- [On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training](https://mlsanity.com/paper/2205.01751/) (2022)
- [D4AM: A General Denoising Framework for Downstream Acoustic Models](https://mlsanity.com/paper/2311.16595/) (2023)
- [Stability Evaluation via Distributional Perturbation Analysis](https://mlsanity.com/paper/2405.03198/) (2024)
- [EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement](https://mlsanity.com/paper/2202.06507/) (2022)
- [Improving the Intent Classification accuracy in Noisy Environment](https://mlsanity.com/paper/2303.06585/) (2023)
- [SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces](https://mlsanity.com/paper/2307.12445/) (2023)
- [TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition](https://mlsanity.com/paper/2404.12979/) (2024)
- [Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognition](https://mlsanity.com/paper/2601.04459/) (2026)
- [Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits](https://mlsanity.com/paper/2602.15405/) (2026)

## Abstract (arXiv)

With the advent of deep learning, research on noise-robust automatic speech recognition (ASR) has progressed rapidly. However, ASR performance in noisy conditions of single-channel systems remains unsatisfactory. Indeed, most single-channel speech enhancement (SE) methods (denoising) have brought only limited performance gains over state-of-the-art ASR back-end trained on multi-condition training data. Recently, there has been much research on neural network-based SE methods working in the time-domain showing levels of performance never attained before. However, it has not been established whether the high enhancement performance achieved by such time-domain approaches could be translated into ASR. In this paper, we show that a single-channel time-domain denoising approach can significantly improve ASR performance, providing more than 30 % relative word error reduction over a strong ASR back-end on the real evaluation data of the single-channel track of the CHiME-4 dataset. These positive results demonstrate that single-channel noise reduction can still improve ASR performance, which should open the door to more research in that direction.