# Light Convolutional Neural Network with Feature Genuinization for Detection of Synthetic Speech Attacks

arXiv: https://arxiv.org/abs/2009.09637 · HTML: https://mlsanity.com/paper/2009.09637/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 23 of 23)

- [ADD 2022: the First Audio Deep Synthesis Detection Challenge](https://mlsanity.com/paper/2202.08433/) (2022)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Half-Truth: A Partially Fake Audio Detection Dataset](https://mlsanity.com/paper/2104.03617/) (2021)
- [Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection](https://mlsanity.com/paper/2406.17376/) (2024)
- [Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks](https://mlsanity.com/paper/2107.08803/) (2021)
- [Forensic deepfake audio detection using segmental speech features](https://mlsanity.com/paper/2505.13847/) (2025)
- [SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection](https://mlsanity.com/paper/2211.06073/) (2022)
- [RW-Resnet: A Novel Speech Anti-Spoofing Model Using Raw Waveform](https://mlsanity.com/paper/2108.05684/) (2021)
- [Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap](https://mlsanity.com/paper/2410.07436/) (2024)
- [Can Emotion Fool Anti-spoofing?](https://mlsanity.com/paper/2505.23962/) (2025)
- [Generalizing Speaker Verification for Spoof Awareness in the Embedding Space](https://mlsanity.com/paper/2401.11156/) (2024)
- [Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprints](https://mlsanity.com/paper/2411.14013/) (2024)
- [Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models](https://mlsanity.com/paper/2506.14153/) (2025)
- [Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection](https://mlsanity.com/paper/2109.02051/) (2021)
- [ConvNeXt Based Neural Network for Audio Anti-Spoofing](https://mlsanity.com/paper/2209.06434/) (2022)
- [Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture](https://mlsanity.com/paper/2210.03581/) (2022)
- [D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack](https://mlsanity.com/paper/2409.07390/) (2024)
- [Unraveling Hidden Representations: A Multi-Modal Layer Analysis for Better Synthetic Content Forensics](https://mlsanity.com/paper/2508.00784/) (2025)
- [Teffic-Audio: Tell Fact from Fiction](https://mlsanity.com/paper/2607.28351/) (2026)
- [Deep Learning Technology for Face Forgery Detection: A Survey](https://mlsanity.com/paper/2409.14289/) (2024)
- [Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection](https://mlsanity.com/paper/2505.24486/) (2025)
- [AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds](https://mlsanity.com/paper/2509.04345/) (2025)
- [HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speech](https://mlsanity.com/paper/2509.21676/) (2025)

## Abstract (arXiv)

Modern text-to-speech (TTS) and voice conversion (VC) systems produce natural sounding speech that questions the security of automatic speaker verification (ASV). This makes detection of such synthetic speech very important to safeguard ASV systems from unauthorized access. Most of the existing spoofing countermeasures perform well when the nature of the attacks is made known to the system during training. However, their performance degrades in face of unseen nature of attacks. In comparison to the synthetic speech created by a wide range of TTS and VC methods, genuine speech has a more consistent distribution. We believe that the difference between the distribution of synthetic and genuine speech is an important discriminative feature between the two classes. In this regard, we propose a novel method referred to as feature genuinization that learns a transformer with convolutional neural network (CNN) using the characteristics of only genuine speech. We then use this genuinization transformer with a light CNN classifier. The ASVspoof 2019 logical access corpus is used to evaluate the proposed method. The studies show that the proposed feature genuinization based LCNN system outperforms other state-of-the-art spoofing countermeasures, depicting its effectiveness for detection of synthetic speech attacks.