Synthetic Speech Source Tracing using Metric Learning
This addresses audio forensic challenges for combating synthetic media manipulation, though it appears incremental by adapting speaker recognition methods.
The paper tackled source tracing in synthetic speech to identify generative systems behind manipulated audio, showing that ResNet with metric learning achieves competitive performance matching or exceeding self-supervised learning systems on the MLAADv5 benchmark.
This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust solutions. We evaluate two approaches: classification-based and metric-learning. We tested our methods on the MLAADv5 benchmark using ResNet and self-supervised learning (SSL) backbones. The results show that ResNet achieves competitive performance with the metric learning approach, matching and even exceeding SSL-based systems. Our work demonstrates ResNet's viability for source tracing while underscoring the need to optimize SSL representations for this task. Our work bridges speaker recognition methodologies with audio forensic challenges, offering new directions for combating synthetic media manipulation.