# Training-Free Intelligibility-Guided Observation Addition for Noisy ASR

arXiv: https://arxiv.org/abs/2602.20967 · HTML: https://mlsanity.com/paper/2602.20967/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [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)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations](https://mlsanity.com/paper/2304.06795/) (2023)
- [MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra](https://mlsanity.com/paper/2305.13686/) (2023)
- [How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR](https://mlsanity.com/paper/2201.06685/) (2022)
- [Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2110.05267/) (2021)
- [Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline](https://mlsanity.com/paper/1803.10109/) (2018)
- [Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech](https://mlsanity.com/paper/2107.10701/) (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)
- [Speech Enhancement Using Continuous Embeddings of Neural Audio Codec](https://mlsanity.com/paper/2502.16240/) (2025)
- [How does end-to-end speech recognition training impact speech enhancement artifacts?](https://mlsanity.com/paper/2311.11599/) (2023)
- [Noise robust speech emotion recognition with signal-to-noise ratio adapting speech enhancement](https://mlsanity.com/paper/2309.01164/) (2023)
- [SNRi Target Training for Joint Speech Enhancement and Recognition](https://mlsanity.com/paper/2111.00764/) (2021)
- [Deep Xi as a Front-End for Robust Automatic Speech Recognition](https://mlsanity.com/paper/1906.07319/) (2019)
- [Towards Decoupling Frontend Enhancement and Backend Recognition in Monaural Robust ASR](https://mlsanity.com/paper/2403.06387/) (2024)
- [From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology](https://mlsanity.com/paper/2412.17778/) (2024)
- [Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module](https://mlsanity.com/paper/2501.02452/) (2025)
- [Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge](https://mlsanity.com/paper/2505.22013/) (2025)

## Abstract (arXiv)

Automatic speech recognition (ASR) degrades severely in noisy environments. Although speech enhancement (SE) front-ends effectively suppress background noise, they often introduce artifacts that harm recognition. Observation addition (OA) addressed this issue by fusing noisy and SE enhanced speech, improving recognition without modifying the parameters of the SE or ASR models. This paper proposes an intelligibility-guided OA method, where fusion weights are derived from intelligibility estimates obtained directly from the backend ASR. Unlike prior OA methods based on trained neural predictors, the proposed method is training-free, reducing complexity and enhances generalization. Extensive experiments across diverse SE-ASR combinations and datasets demonstrate strong robustness and improvements over existing OA baselines. Additional analyses of intelligibility-guided switching-based alternatives and frame versus utterance-level OA further validate the proposed design.