Audio Adversarial Examples: Attacks Using Vocal Masks
arXiv:2102.02417
Abstract
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.
arXiv comment9 pages, 1 figure, 2 tables. Submitted to COLING2020
References in corpus (4)
- Explaining and Harnessing Adversarial Examples
- Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques
- Singing Voice Separation and Vocal F0 Estimation based on Mutual Combination of Robust Principal Component Analysis and Subharmonic Summation
- Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network