# Towards End-to-End Synthetic Speech Detection

arXiv: https://arxiv.org/abs/2106.06341 · HTML: https://mlsanity.com/paper/2106.06341/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2021.

## Built on by (most cited first, 30 of 38)

- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0](https://mlsanity.com/paper/2409.11909/) (2024)
- [SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing](https://mlsanity.com/paper/2211.02718/) (2022)
- [Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook](https://mlsanity.com/paper/2411.19537/) (2024)
- [FairSSD: Understanding Bias in Synthetic Speech Detectors](https://mlsanity.com/paper/2404.10989/) (2024)
- [CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning](https://mlsanity.com/paper/2404.15854/) (2024)
- [Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck](https://mlsanity.com/paper/2204.01387/) (2022)
- [TBFormer: Two-Branch Transformer for Image Forgery Localization](https://mlsanity.com/paper/2302.13004/) (2023)
- [An Overview of Recent Work in Media Forensics: Methods and Threats](https://mlsanity.com/paper/2204.12067/) (2022)
- [Retrieval-Augmented Audio Deepfake Detection](https://mlsanity.com/paper/2404.13892/) (2024)
- [Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study](https://mlsanity.com/paper/2509.07132/) (2025)
- [FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection](https://mlsanity.com/paper/2110.09441/) (2021)
- [DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection](https://mlsanity.com/paper/2304.03323/) (2023)
- [Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection](https://mlsanity.com/paper/2310.08869/) (2023)
- [VoiceWukong: Benchmarking Deepfake Voice Detection](https://mlsanity.com/paper/2409.06348/) (2024)
- [Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection](https://mlsanity.com/paper/2601.23066/) (2026)
- [DiffSSD: A Diffusion-Based Dataset For Speech Forensics](https://mlsanity.com/paper/2409.13049/) (2024)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [Generalizing Speaker Verification for Spoof Awareness in the Embedding Space](https://mlsanity.com/paper/2401.11156/) (2024)
- [SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks](https://mlsanity.com/paper/2507.13170/) (2025)
- [Targeted Augmented Data for Audio Deepfake Detection](https://mlsanity.com/paper/2407.07598/) (2024)
- [Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development](https://mlsanity.com/paper/2109.01164/) (2021)
- [ConvNeXt Based Neural Network for Audio Anti-Spoofing](https://mlsanity.com/paper/2209.06434/) (2022)
- [Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion](https://mlsanity.com/paper/2305.16353/) (2023)
- [Exploring Green AI for Audio Deepfake Detection](https://mlsanity.com/paper/2403.14290/) (2024)
- [Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples](https://mlsanity.com/paper/2408.13341/) (2024)
- [FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning](https://mlsanity.com/paper/2504.15663/) (2025)
- [DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities](https://mlsanity.com/paper/2606.04205/) (2026)
- [Adaptive re-calibration of channel-wise features for Adversarial Audio Classification](https://mlsanity.com/paper/2210.11722/) (2022)
- [An End-to-End Multi-Module Audio Deepfake Generation System for ADD Challenge 2023](https://mlsanity.com/paper/2307.00729/) (2023)

## Abstract (arXiv)

The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature extraction and a back-end binary classifier, or a deep neural network (DNN) directly for further feature extraction and classification. Despite the rich literature on such a pipeline, we show in this paper that the pre-transform and hand-crafted features could simply be replaced by end-to-end DNNs. Specifically, we experimentally verify that by only using standard components, a light-weight neural network could outperform the state-of-the-art methods for the ASVspoof2019 challenge. The proposed model is termed Time-domain Synthetic Speech Detection Net (TSSDNet), having ResNet- or Inception-style structures. We further demonstrate that the proposed models also have attractive generalization capability. Trained on ASVspoof2019, they could achieve promising detection performance when tested on disjoint ASVspoof2015, significantly better than the existing cross-dataset results. This paper reveals the great potential of end-to-end DNNs for synthetic speech detection, without hand-crafted features.