TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models

• URL: http://arxiv.org/abs/2604.01083v1
• Date: Wed, 01 Apr 2026 16:12:31 GMT
• Title: TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models
• Abstract summary: We propose TRACE (Training-free Representation-based Audio Countermeasure via Embedding dynamics) to detect partial audio deepfakes.<n>TRACE analyzes the first-order dynamics of frozen speech foundation model representations without any training, labeled data, or architectural modification.<n>We evaluate TRACE on four benchmarks that span two languages using six speech foundation models.
• Score: 6.951909224842812
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Partial audio deepfakes, where synthesized segments are spliced into genuine recordings, are particularly deceptive because most of the audio remains authentic. Existing detectors are supervised: they require frame-level annotations, overfit to specific synthesis pipelines, and must be retrained as new generative models emerge. We argue that this supervision is unnecessary. We hypothesize that speech foundation models implicitly encode a forensic signal: genuine speech forms smooth, slowly varying embedding trajectories, while splice boundaries introduce abrupt disruptions in frame-level transitions. Building on this, we propose TRACE (Training-free Representation-based Audio Countermeasure via Embedding dynamics), a training-free framework that detects partial audio deepfakes by analyzing the first-order dynamics of frozen speech foundation model representations without any training, labeled data, or architectural modification. We evaluate TRACE on four benchmarks that span two languages using six speech foundation models. In PartialSpoof, TRACE achieves 8.08% EER, competitive with fine-tuned supervised baselines. In LlamaPartialSpoof, the most challenging benchmark featuring LLM-driven commercial synthesis, TRACE surpasses a supervised baseline outright (24.12% vs. 24.49% EER) without any target-domain data. These results show that temporal dynamics in speech foundation models provide an effective, generalize signal for training-free audio forensics.

Related papers

• From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data [8.018854030707912]
  We present a synthetic-to-real training paradigm that supports multilingual data without requiring parallel corpora or explicit alignment.<n>Experiments across multiple languages demonstrate that the proposed approach achieves high naturalness and strong speaker similarity, despite being trained exclusively on English data.
  arXiv  Detail & Related papers  (2026-06-07T21:25:14Z)
• AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following [17.52339026461815]
  We introduce a novel dynamic rubric-based evaluation paradigm that adaptively decomposes complex audio captions into a variable number of independent, verifiable binary rubric items.<n>We benchmark this capability with the AnyAudio-Judge Bench, a comprehensive, bilingual benchmark comprising 7,920 meticulously curated samples.<n>Experiments demonstrate that AnyAudio-Judge not only significantly enhances zero-shot alignment detection compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-02T04:00:32Z)
• PACE: Pretrained Audio Continual Learning [27.605574463021693]
  We present the first systematic benchmark for audio continual learning (CL) with pretrained models (PTMs)<n>In addition, we introduce spectrogram-based boundary-aware perturbations to mitigate representation overlap and improve stability.<n>Experiments on six diverse audio CL benchmarks demonstrate that PACE substantially outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:28:35Z)
• Representation-Regularized Convolutional Audio Transformer for Audio Understanding [53.092757178419355]
  bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge.<n>We propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2026-01-29T12:16:19Z)
• AURORA: Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation [113.75682363364004]
  AURORA is a framework designed to enhance genuine reasoning and language comprehension in reference audio-visual segmentation.<n>AURORA achieves state-of-the-art performance on Ref-AVS benchmarks and generalizes effectively to unreferenced segmentation.
  arXiv  Detail & Related papers  (2025-08-04T07:47:38Z)
• TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization [7.448652734290433]
  We tackle the specific task of sound-prompted segmentation, aiming to segment image regions corresponding to objects heard in an audio signal.<n>Most existing approaches tackle this problem by fine-tuning pre-trained models or by training additional modules specifically for the task.<n>We adopt a different strategy: we introduce a training-free approach that leverages Non-negative Matrix Factorization (NMF) to co-factorize audio and visual features from pre-trained models so as to reveal shared interpretable concepts.
  arXiv  Detail & Related papers  (2024-12-02T13:39:49Z)
• REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR [54.64158282822995]
  We propose REBORN,Reinforcement-Learned Boundary with Iterative Training for Unsupervised ASR. ReBORN alternates between training a segmentation model that predicts the boundaries of the segmental structures in speech signals and training the phoneme prediction model, whose input is the speech feature segmented by the segmentation model, to predict a phoneme transcription. We conduct extensive experiments and find that under the same setting, REBORN outperforms all prior unsupervised ASR models on LibriSpeech, TIMIT, and five non-English languages in Multilingual LibriSpeech.
  arXiv  Detail & Related papers  (2024-02-06T13:26:19Z)
• High-Fidelity Speech Synthesis with Minimal Supervision: All Using Diffusion Models [56.00939852727501]
  Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations. Non-autoregressive framework enhances controllability, and duration diffusion model enables diversified prosodic expression.
  arXiv  Detail & Related papers  (2023-09-27T09:27:03Z)
• ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification [42.95038619688867]
  ASiT is a novel self-supervised learning framework that captures local and global contextual information by employing group masked model learning and self-distillation. We evaluate our pretrained models on both audio and speech classification tasks, including audio event classification, keyword spotting, and speaker identification.
  arXiv  Detail & Related papers  (2022-11-23T18:21:09Z)
• Revisiting End-to-End Speech-to-Text Translation From Scratch [48.203394370942505]
  End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks. In this paper, we explore the extent to which the quality of E2E ST trained on speech-translation pairs alone can be improved.
  arXiv  Detail & Related papers  (2022-06-09T15:39:19Z)
• SSAST: Self-Supervised Audio Spectrogram Transformer [19.09439093130855]
  We propose to pretrain the Audio Spectrogram Transformer (AST) model with joint discriminative and generative masked spectrogram patch modeling (MSPM) using unlabeled audio. We evaluate our pretrained models on both audio and speech classification tasks including audio event classification, keyword spotting, emotion recognition, and speaker identification. To the best of our knowledge, it is the first patch-based self-supervised learning framework in the audio and speech domain, and also the first self-supervised learning framework for AST.
  arXiv  Detail & Related papers  (2021-10-19T07:58:28Z)
• Direct speech-to-speech translation with discrete units [64.19830539866072]
  We present a direct speech-to-speech translation (S2ST) model that translates speech from one language to speech in another language without relying on intermediate text generation. We propose to predict the self-supervised discrete representations learned from an unlabeled speech corpus instead. When target text transcripts are available, we design a multitask learning framework with joint speech and text training that enables the model to generate dual mode output (speech and text) simultaneously in the same inference pass.
  arXiv  Detail & Related papers  (2021-07-12T17:40:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.