# Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling

arXiv: https://arxiv.org/abs/1903.04567 · HTML: https://mlsanity.com/paper/1903.04567/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2019.

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

- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022)
- [LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement](https://mlsanity.com/paper/2503.00493/) (2025)
- [Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2110.05267/) (2021)
- [Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2203.14838/) (2022)
- [LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers](https://mlsanity.com/paper/2211.02809/) (2022)
- [Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR](https://mlsanity.com/paper/2304.04974/) (2023)
- [Investigating the Design Space of Diffusion Models for Speech Enhancement](https://mlsanity.com/paper/2312.04370/) (2023)
- [TSELM: Target Speaker Extraction using Discrete Tokens and Language Models](https://mlsanity.com/paper/2409.07841/) (2024)
- [Noise-aware Speech Enhancement using Diffusion Probabilistic Model](https://mlsanity.com/paper/2307.08029/) (2023)
- [Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancement](https://mlsanity.com/paper/2406.13471/) (2024)
- [SE-Bridge: Speech Enhancement with Consistent Brownian Bridge](https://mlsanity.com/paper/2305.13796/) (2023)
- [Speech Enhancement Using Continuous Embeddings of Neural Audio Codec](https://mlsanity.com/paper/2502.16240/) (2025)
- [On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings](https://mlsanity.com/paper/2306.03014/) (2023)
- [LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models](https://mlsanity.com/paper/2504.07402/) (2025)
- [Aligning Generative Speech Enhancement with Perceptual Feedback](https://mlsanity.com/paper/2507.09929/) (2025)
- [ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning](https://mlsanity.com/paper/2312.06118/) (2023)
- [D4AM: A General Denoising Framework for Downstream Acoustic Models](https://mlsanity.com/paper/2311.16595/) (2023)
- [Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation](https://mlsanity.com/paper/2406.10276/) (2024)
- [Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognition](https://mlsanity.com/paper/2601.04459/) (2026)

## Abstract (arXiv)

Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the distortion problem, compare different acoustic models, and investigate a distortion-independent training scheme for monaural speech recognition. Experimental results suggest that distortion-independent acoustic modeling is able to overcome the distortion problem. Such an acoustic model can also work with speech enhancement models different from the one used during training. Moreover, the models investigated in this paper outperform the previous best system on the CHiME-2 corpus.