# Data Quality as Predictor of Voice Anti-Spoofing Generalization

arXiv: https://arxiv.org/abs/2103.14602 · HTML: https://mlsanity.com/paper/2103.14602/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 10 of 10)

- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [Probing the Information Encoded in X-vectors](https://mlsanity.com/paper/1909.06351/) (2019)
- [An explainability study of the constant Q cepstral coefficient spoofing countermeasure for automatic speaker verification](https://mlsanity.com/paper/2004.06422/) (2020)
- [Generalization of Spoofing Countermeasures: a Case Study with ASVspoof 2015 and BTAS 2016 Corpora](https://mlsanity.com/paper/1901.08025/) (2019)
- [Introduction to Voice Presentation Attack Detection and Recent Advances](https://mlsanity.com/paper/1901.01085/) (2019)
- [Ensemble Models for Spoofing Detection in Automatic Speaker Verification](https://mlsanity.com/paper/1904.04589/) (2019)
- [ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems](https://mlsanity.com/paper/1904.03365/) (2019)
- [Spoofing Detection Goes Noisy: An Analysis of Synthetic Speech Detection in the Presence of Additive Noise](https://mlsanity.com/paper/1603.03947/) (2016)
- [Dataset artefacts in anti-spoofing systems: a case study on the ASVspoof 2017 benchmark](https://mlsanity.com/paper/2010.07913/) (2020)
- [Subband modeling for spoofing detection in automatic speaker verification](https://mlsanity.com/paper/2004.01922/) (2020)

## Built on by (most cited first, 6 of 6)

- [Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing](https://mlsanity.com/paper/2305.19953/) (2023)
- [Shortcut Learning in Binary Classifier Black Boxes: Applications to Voice Anti-Spoofing and Biometrics](https://mlsanity.com/paper/2601.17782/) (2026)
- [Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization](https://mlsanity.com/paper/2302.05110/) (2023)
- [Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems](https://mlsanity.com/paper/2509.09204/) (2025)
- [Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing](https://mlsanity.com/paper/2406.17246/) (2024)
- [Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification](https://mlsanity.com/paper/2310.00602/) (2023)

## Abstract (arXiv)

Voice anti-spoofing aims at classifying a given utterance either as a bonafide human sample, or a spoofing attack (e.g. synthetic or replayed sample). Many anti-spoofing methods have been proposed but most of them fail to generalize across domains (corpora) -- and we do not know why. We outline a novel interpretative framework for gauging the impact of data quality upon anti-spoofing performance. Our within- and between-domain experiments pool data from seven public corpora and three anti-spoofing methods based on Gaussian mixture and convolutive neural network models. We assess the impacts of long-term spectral information, speaker population (through x-vector speaker embeddings), signal-to-noise ratio, and selected voice quality features.