# MP3 Compression To Diminish Adversarial Noise in End-to-End Speech Recognition

arXiv: https://arxiv.org/abs/2007.12892 · HTML: https://mlsanity.com/paper/2007.12892/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Dompteur: Taming Audio Adversarial Examples](https://mlsanity.com/paper/2102.05431/) (2021)
- [SEC4SR: A Security Analysis Platform for Speaker Recognition](https://mlsanity.com/paper/2109.01766/) (2021)
- [MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems](https://mlsanity.com/paper/2303.05758/) (2023)
- [Codec-Robust Attacks on Audio LLMs](https://mlsanity.com/paper/2605.20519/) (2026)
- [Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence](https://mlsanity.com/paper/2112.13060/) (2021)

## Abstract (arXiv)

Audio Adversarial Examples (AAE) represent specially created inputs meant to trick Automatic Speech Recognition (ASR) systems into misclassification. The present work proposes MP3 compression as a means to decrease the impact of Adversarial Noise (AN) in audio samples transcribed by ASR systems. To this end, we generated AAEs with the Fast Gradient Sign Method for an end-to-end, hybrid CTC-attention ASR system. Our method is then validated by two objective indicators: (1) Character Error Rates (CER) that measure the speech decoding performance of four ASR models trained on uncompressed, as well as MP3-compressed data sets and (2) Signal-to-Noise Ratio (SNR) estimated for both uncompressed and MP3-compressed AAEs that are reconstructed in the time domain by feature inversion. We found that MP3 compression applied to AAEs indeed reduces the CER when compared to uncompressed AAEs. Moreover, feature-inverted (reconstructed) AAEs had significantly higher SNRs after MP3 compression, indicating that AN was reduced. In contrast to AN, MP3 compression applied to utterances augmented with regular noise resulted in more transcription errors, giving further evidence that MP3 encoding is effective in diminishing only AN.