# SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech

arXiv: https://arxiv.org/abs/2505.09616 · HTML: https://mlsanity.com/paper/2505.09616/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 10 Jan 2025.

## Builds on (most cited first, 2 of 2)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion](https://mlsanity.com/paper/2210.15418/) (2022)

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

- [The First VoicePrivacy Attacker Challenge](https://mlsanity.com/paper/2504.14183/) (2025)
- [SegReConcat: A Data Augmentation Method for Voice Anonymization Attack](https://mlsanity.com/paper/2508.18907/) (2025)
- [DAST: A Dual-Stream Voice Anonymization Attacker with Staged Training](https://mlsanity.com/paper/2603.12840/) (2026)
- [Evaluating Identity Leakage in Speaker De-Identification Systems](https://mlsanity.com/paper/2508.14012/) (2025)
- [Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification](https://mlsanity.com/paper/2609.18673/) (2026)

## Abstract (arXiv)

This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction and incorporates spectrogram resizing and incremental training for improved performance. Evaluated on librispeech-dev and librispeech-test, SpecWav-Attack outperforms conventional attacks, revealing vulnerabilities in anonymized speech systems and emphasizing the need for stronger defenses, benchmarked against the ICASSP 2025 Attacker Challenge.