mlsanityData to 14 Oct 2026

Synthetic Speech Source Tracing using Metric Learning

arXiv 2506.02590 ↗First posted 3 Jun 2025cs.SD cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 19 of its 23 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

19 of 23 references.

References · 19

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  5. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  6. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  8. 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
  9. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 273
  10. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  11. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  12. 2020In defence of metric learning for speaker recognitioncited by 126
7 more
  1. 2024MLAAD: The Multi-Language Audio Anti-Spoofing Datasetcited by 56
  2. 2018Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition Systemcited by 47
  3. 2023The Tunnel Effect: Building Data Representations in Deep Neural Networkscited by 34
  4. 2024Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generatorscited by 18
  5. 2024Source Tracing of Audio Deepfake Systemscited by 15
  6. 2022An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audiocited by 14
  7. 2019Delving into VoxCeleb: environment invariant speaker recognitioncited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracingcited by 2
  2. 2026Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learningcited by 1
  3. 2026Open-Set Source Tracing as Compositional Factors via Structured Prototypescited by 1
  4. 2026SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detectioncited by 0