# Impact of Phonetics on Speaker Identity in Adversarial Voice Attack

arXiv: https://arxiv.org/abs/2509.15437 · HTML: https://mlsanity.com/paper/2509.15437/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [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)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [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)
- [Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems](https://mlsanity.com/paper/1911.01840/) (2019)
- [CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition](https://mlsanity.com/paper/1801.08535/) (2018)
- [End-to-End Text-Dependent Speaker Verification](https://mlsanity.com/paper/1509.08062/) (2015)
- [Robust Audio Adversarial Example for a Physical Attack](https://mlsanity.com/paper/1810.11793/) (2018)
- [Fooling End-to-end Speaker Verification by Adversarial Examples](https://mlsanity.com/paper/1801.03339/) (2018)
- [AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models](https://mlsanity.com/paper/2412.08608/) (2024)
- [Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems](https://mlsanity.com/paper/2003.02301/) (2020)
- [Adversarial Attacks on GMM i-vector based Speaker Verification Systems](https://mlsanity.com/paper/1911.03078/) (2019)
- [Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning](https://mlsanity.com/paper/2106.00273/) (2021)
- [The Impact of Silence on Speech Anti-Spoofing](https://mlsanity.com/paper/2309.11827/) (2023)
- [Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model](https://mlsanity.com/paper/2408.09300/) (2024)
- [Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systems](https://mlsanity.com/paper/2206.09103/) (2022)
- [PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection](https://mlsanity.com/paper/2309.06960/) (2023)
- [Neural Codec-based Adversarial Sample Detection for Speaker Verification](https://mlsanity.com/paper/2406.04582/) (2024)
- [Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models](https://mlsanity.com/paper/2409.07936/) (2024)

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

- [Probing Speaker Identity Sensitivity in Audio Deepfake Detectors](https://mlsanity.com/paper/2607.21820/) (2026)

## Abstract (arXiv)

Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain imperceptible to humans but can significantly alter system outputs. While targeted attacks on end-to-end ASR models have been widely studied, the phonetic basis of these perturbations and their effect on speaker identity remain underexplored. In this work, we analyze adversarial audio at the phonetic level and show that perturbations exploit systematic confusions such as vowel centralization and consonant substitutions. These distortions not only mislead transcription but also degrade phonetic cues critical for speaker verification, leading to identity drift. Using DeepSpeech as our ASR target, we generate targeted adversarial examples and evaluate their impact on speaker embeddings across genuine and impostor samples. Results across 16 phonetically diverse target phrases demonstrate that adversarial audio induces both transcription errors and identity drift, highlighting the need for phonetic-aware defenses to ensure the robustness of ASR and speaker recognition systems.