A Practical Guide to Logical Access Voice Presentation Attack Detection
It addresses the growing threat of voice spoofing attacks in human-machine interfaces, offering a resource for practitioners, but is incremental as it synthesizes existing knowledge rather than introducing new breakthroughs.
This chapter provides a practical guide to voice presentation attack detection (PAD) for automatic speaker verification, focusing on logical access attacks using text-to-speech and voice conversion, and includes an experimental study with open-sourced code on a benchmark dataset.
Voice-based human-machine interfaces with an automatic speaker verification (ASV) component are commonly used in the market. However, the threat from presentation attacks is also growing since attackers can use recent speech synthesis technology to produce a natural-sounding voice of a victim. Presentation attack detection (PAD) for ASV, or speech anti-spoofing, is therefore indispensable. Research on voice PAD has seen significant progress since the early 2010s, including the advancement in PAD models, benchmark datasets, and evaluation campaigns. This chapter presents a practical guide to the field of voice PAD, with a focus on logical access attacks using text-to-speech and voice conversion algorithms and spoofing countermeasures based on artifact detection. It introduces the basic concept of voice PAD, explains the common techniques, and provides an experimental study using recent methods on a benchmark dataset. Code for the experiments is open-sourced.