# Audio Adversarial Examples: Attacks Using Vocal Masks

arXiv: https://arxiv.org/abs/2102.02417 · HTML: https://mlsanity.com/paper/2102.02417/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 40 references that are in the map.
- First posted on arXiv 4 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding](https://mlsanity.com/paper/1808.05665/) (2018)
- [DolphinAtack: Inaudible Voice Commands](https://mlsanity.com/paper/1708.09537/) (2017)
- [RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation](https://mlsanity.com/paper/1905.03072/) (2019)
- [Scaling Up Online Speech Recognition Using ConvNets](https://mlsanity.com/paper/2001.09727/) (2020)
- [Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network](https://mlsanity.com/paper/1504.04658/) (2015)
- [Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy](https://mlsanity.com/paper/1812.01278/) (2018)
- [Singing Voice Separation and Vocal F0 Estimation based on Mutual Combination of Robust Principal Component Analysis and Subharmonic Summation](https://mlsanity.com/paper/1604.00192/) (2016)

## Abstract (arXiv)

We construct audio adversarial examples on automatic Speech-To-Text systems . Given any audio waveform, we produce an another by overlaying an audio vocal mask generated from the original audio. We apply our audio adversarial attack to five SOTA STT systems: DeepSpeech, Julius, Kaldi, wav2letter@anywhere and CMUSphinx. In addition, we engaged human annotators to transcribe the adversarial audio. Our experiments show that these adversarial examples fool State-Of-The-Art Speech-To-Text systems, yet humans are able to consistently pick out the speech. The feasibility of this attack introduces a new domain to study machine and human perception of speech.