# Assessing the Impact of Noise and Speech Enhancement on the Intelligibility of Speech Codecs

arXiv: https://arxiv.org/abs/2605.03776 · HTML: https://mlsanity.com/paper/2605.03776/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 5 May 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, 20 of 20)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [LPCNet: Improving Neural Speech Synthesis Through Linear Prediction](https://mlsanity.com/paper/1810.11846/) (2018)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound](https://mlsanity.com/paper/2405.00233/) (2024)
- [Scaling Transformers for Low-Bitrate High-Quality Speech Coding](https://mlsanity.com/paper/2411.19842/) (2024)
- [Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST](https://mlsanity.com/paper/2509.14128/) (2025)
- [SCOREQ: Speech Quality Assessment with Contrastive Regression](https://mlsanity.com/paper/2410.06675/) (2024)
- [DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio](https://mlsanity.com/paper/2205.05474/) (2022)
- [TS3-Codec: Transformer-Based Simple Streaming Single Codec](https://mlsanity.com/paper/2411.18803/) (2024)
- [Generative Speech Coding with Predictive Variance Regularization](https://mlsanity.com/paper/2102.09660/) (2021)
- [Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance](https://mlsanity.com/paper/2404.14860/) (2024)
- [Crowdsourced Multilingual Speech Intelligibility Testing](https://mlsanity.com/paper/2403.14817/) (2024)
- [Probing the Robustness Properties of Neural Speech Codecs](https://mlsanity.com/paper/2505.24248/) (2025)
- [Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer](https://mlsanity.com/paper/2410.08325/) (2024)
- [Low-Resource Audio Codec (LRAC): 2025 Challenge Description](https://mlsanity.com/paper/2510.23312/) (2025)
- [Benchmarking Neural Speech Codec Intelligibility with SITool](https://mlsanity.com/paper/2506.01731/) (2025)
- [Enhancing Noise Robustness for Neural Speech Codecs through Resource-Efficient Progressive Quantization Perturbation Simulation](https://mlsanity.com/paper/2509.19025/) (2025)

## Built on by (most cited first, 1 of 1)

- [Objective Intelligibility Prediction Using Distance Metrics on Speech Foundation Model Representations](https://mlsanity.com/paper/2609.13046/) (2026)

## Abstract (arXiv)

Preserving speech intelligibility is a minimum requirement for speech codecs in communication. Recently, very low-bitrate neural codecs have gained interest for replacing classical codecs, reinforcing the need to evaluate whether intelligibility is preserved in realistic scenarios. In this paper, we evaluate the intelligibility and listening effort of classical and neural speech codecs in clean and noisy conditions. Further, we assess the impact of speech enhancement (SE) before coding, simulating a possible audio processing pipeline. The results show that classical codecs are more noise robust than neural codecs. Further, SE can lead to significant intelligibility and listening effort improvements for codecs otherwise negatively affected by noise. Listening effort reveals nuanced differences when intelligibility is saturated. Lastly, objective intelligibility based on automatic speech recognition is highly correlated with subjective intelligibility scores averaged per condition.