# Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders

arXiv: https://arxiv.org/abs/2210.10570 · HTML: https://mlsanity.com/paper/2210.10570/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2022.

## Built on by (most cited first, 20 of 20)

- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [SpoofCeleb: Speech Deepfake Detection and SASV In The Wild](https://mlsanity.com/paper/2409.17285/) (2024)
- [One-Class Knowledge Distillation for Spoofing Speech Detection](https://mlsanity.com/paper/2309.08285/) (2023)
- [SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection](https://mlsanity.com/paper/2407.18517/) (2024)
- [Towards single integrated spoofing-aware speaker verification embeddings](https://mlsanity.com/paper/2305.19051/) (2023)
- [Collaborative Watermarking for Adversarial Speech Synthesis](https://mlsanity.com/paper/2309.15224/) (2023)
- [Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing](https://mlsanity.com/paper/2409.08346/) (2024)
- [Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge](https://mlsanity.com/paper/2410.07379/) (2024)
- [SZU-AFS Antispoofing System for the ASVspoof 5 Challenge](https://mlsanity.com/paper/2408.09933/) (2024)
- [Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching](https://mlsanity.com/paper/2503.18032/) (2025)
- [AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection](https://mlsanity.com/paper/2603.26856/) (2026)
- [A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations](https://mlsanity.com/paper/2506.03425/) (2025)
- [Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper](https://mlsanity.com/paper/2602.22658/) (2026)
- [Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment](https://mlsanity.com/paper/2509.23618/) (2025)
- [On Deepfake Voice Detection -- It's All in the Presentation](https://mlsanity.com/paper/2509.26471/) (2025)
- [Ethical and Technical Limits of Deepfake Speech Datasets](https://mlsanity.com/paper/2606.10911/) (2026)
- [BEAT2AASIST model with layer fusion for ESDD 2026 Challenge](https://mlsanity.com/paper/2512.15180/) (2025)
- [Echoes: A semantically-aligned music deepfake detection dataset](https://mlsanity.com/paper/2603.23667/) (2026)
- [A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators](https://mlsanity.com/paper/2603.27557/) (2026)
- [Tracing Decoder Artifacts for Compact Synthetic Speech Screening](https://mlsanity.com/paper/2609.32050/) (2026)

## Abstract (arXiv)

A good training set for speech spoofing countermeasures requires diverse TTS and VC spoofing attacks, but generating TTS and VC spoofed trials for a target speaker may be technically demanding. Instead of using full-fledged TTS and VC systems, this study uses neural-network-based vocoders to do copy-synthesis on bona fide utterances. The output data can be used as spoofed data. To make better use of pairs of bona fide and spoofed data, this study introduces a contrastive feature loss that can be plugged into the standard training criterion. On the basis of the bona fide trials from the ASVspoof 2019 logical access training set, this study empirically compared a few training sets created in the proposed manner using a few neural non-autoregressive vocoders. Results on multiple test sets suggest good practices such as fine-tuning neural vocoders using bona fide data from the target domain. The results also demonstrated the effectiveness of the contrastive feature loss. Combining the best practices, the trained CM achieved overall competitive performance. Its EERs on the ASVspoof 2021 hidden subsets also outperformed the top-1 challenge submission.