Synthetic Speech Source Tracing using Metric Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Metric LearningSelf-Supervised LearningSpeaker RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation
We present a novel approach to improve the performance of learning-based speech dereverberation using accurate synthetic datasets. Our approach is designed to recover the reverb-free signal from a reverberant speech sign…
Speech DereverberationUnveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusion
Audio deepfakes are acquiring an unprecedented level of realism with advanced AI. While current research focuses on discerning real speech from spoofed speech, tracing the source system is equally crucial. This work prop…
Face SwappingMetric LearningSource Tracing of Synthetic Speech Systems Through Paralinguistic Pre-Trained Representations
In this work, we focus on source tracing of synthetic speech generation systems (STSGS). Each source embeds distinctive paralinguistic features--such as pitch, tone, rhythm, and intonation--into their synthesized speech,…
Emotion RecognitionRhythmSpeaker RecognitionSpeech Emotion Recognition+1Towards Generalized Source Tracing for Codec-Based Deepfake Speech
Recent attempts at source tracing for codec-based deepfake speech (CodecFake), generated by neural audio codec-based speech generation (CoSG) models, have exhibited suboptimal performance. However, how to train source tr…
Face SwappingOpen-Set Source Tracing as Compositional Factors via Structured Prototypes
Recent research expands beyond binary anti-spoofing with the emergence of Source Tracing, the task of identifying the specific generative origins of synthetic speech. However, current research often equates a "source" wi…