Temporal Anchors and Editing Sensitivity in Partial Speech Spoofing: A Controlled Study

Xiaosu Su; Yun Cao; Yiping Ni; Xiaowei Yi

cs.SDOct 3, 2026

Temporal Anchors and Editing Sensitivity in Partial Speech Spoofing: A Controlled Study

Authors: Xiaosu Su, Yun Cao, Yiping Ni, Xiaowei Yi

Organizations: Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100085, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100085, China

Abstract

Partial-spoof detectors must reject synthetic content while accepting benign edits. We diagnose temporal anchors and boundary-consistency training using frozen WavLM features, nonlinguistic unit controls, and source-locked evaluation. Genuine-genuine and genuine-fake splices contrast editing false alarms with synthetic-content misses; they do not isolate a unique causal artifact. With layer-6 features, phone units have higher PartialSpoof evaluation frame EER than soft frames (11.18% versus 9.59%). In 500 retrospective PS-eval cases, augmentation reduces genuine-splice false alarms; synthetic-core misses increase at 5% PS-development FPR but not demonstrably at 1%. A 200-case Llama A follow-up retains the false-alarm reduction but does not establish a miss-rate increase. Constructed-case ranking can improve while fixed-threshold misses rise. Consistency gives no uniform gain, and encoder-layer rankings change across corpora. We report frame and event localization with three seeds, including word units, and treat PS evaluation as retrospective. Audit code, selected training scripts, and result summaries are available at https://github.com/mysxs/partial-spoof-diagnostics.

Figures & tables

System	PS dev	PS eval	HAD test	Llama A	Llama B
WavLM final, hard frame	$5.330\pm 0.127$	$11.123\pm 0.020$	$38.589\pm 1.009$	$42.413\pm 0.444$	$38.587\pm 0.119$
WavLM layer 6, hard frame	$1.738\pm 0.043$	$9.772\pm 0.487$	$56.582\pm 5.003$	$41.493\pm 0.638$	$41.245\pm 0.069$
WavLM layer 12, hard frame	$2.716\pm 0.094$	$8.278\pm 0.418$	$38.735\pm 3.323$	$40.815\pm 0.177$	$35.701\pm 0.089$
Released reCFPRF	—	9.826	14.862	41.673	40.512

Table 1: 20-ms frame EER (%). Probe rows give three-seed mean

\pm

sample SD. Layer 6 is selected on PS development data; layer 12 is a reported comparison, not a target-selected replacement. Released reCFPRF has a different encoder/training recipe and is one checkpoint.

Arm	EER	Frame F1	Frame R	Event P	Event R	Event F1	Short R
Hard frame	$11.123\pm 0.020$	$85.945\pm 0.010$	$82.420\pm 0.341$	$47.472\pm 0.973$	$66.763\pm 0.931$	$55.479\pm 0.505$	$60.957\pm 1.788$
Soft frame	$11.326\pm 0.132$	$85.657\pm 0.135$	$82.267\pm 0.556$	$47.242\pm 0.777$	$63.565\pm 0.325$	$54.199\pm 0.572$	$53.984\pm 0.629$
Phone unit	$11.237\pm 0.224$	$86.030\pm 0.314$	$83.904\pm 0.817$	$57.944\pm 1.735$	$43.823\pm 0.697$	$49.888\pm 0.394$	$15.694\pm 1.375$
Word unit	$12.514\pm 0.182$	$84.624\pm 0.311$	$82.657\pm 0.594$	$61.313\pm 0.716$	$39.665\pm 0.459$	$48.169\pm 0.559$	$11.730\pm 0.221$

Table 2: Complete PS-eval localization audit from frozen final-layer predictions (three seeds; percentages, mean

\pm

sample SD). Frame F1/recall use official 20-ms labels. Event P/R/F1 match predicted and original 10-ms reference spans at IoU

\geq 0.5

; short R is recall for reference events shorter than 100 ms. PS eval is retrospective.

Prediction / context	Frame EER	Event F1	Short R
Hard frame	$9.772\pm 0.487$	—	—
Soft frame	$9.591\pm 0.284$	$64.297\pm 0.400$	$68.722\pm 1.510$
Phone-unit output	$11.180\pm 0.444$	$52.291\pm 0.296$	$20.704\pm 0.610$
Frame + phone context	$9.656\pm 0.410$	—	—
Frame + duplicated frame	$9.928\pm 0.541$	—	—
Frame + fixed 80 ms	$10.176\pm 0.661$	—	—

Table 3: Layer-6 PS-eval probes (three-seed mean

\pm

SD, %). Event metrics audit the same soft-frame and phone-unit checkpoints at saved PS-dev thresholds; context arms were not audited.

Unit	Training	G	GG	GF	GF50
Frame	Original	2.89	25.63	8.98	7.18
Frame	Augment	2.38	5.48	22.31	20.72
Frame	+Consistency	3.23	6.41	20.52	19.60
Phone	Original	2.37	27.80	13.12	14.76
Phone	Augment	1.97	4.33	29.95	29.61
Phone	+Consistency	1.99	3.47	31.66	31.83

Table 4: Supplementary controls: 500 cases, 48 speakers, three-seed means (%), original dev-EER thresholds. G/GG: unedited/genuine-splice FPR; GF/GF50: raw/50-ms-smoothed synthetic-core FNR. Final-layer models; lower is better.

		Dev 1%		Dev 5%
Unit	Training	GG–G	GF	GG–G	GF
Frame	Original	8.48	33.90	21.61	9.90
Frame	Augment	1.06	35.01	2.86	23.21
Frame	+Consistency	1.20	34.95	2.95	21.48
Phone	Original	8.68	47.64	22.97	15.72
Phone	Augment	0.65	49.48	2.03	32.21

Table 5: The same controls at dev-calibrated 1%/5% FPR thresholds (three-seed means, %). GG–G is genuine-splice FPR minus unedited genuine FPR; GF is synthetic-core FNR. Target-domain FPR is not fixed.

Explore similar work

TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models
Apr 1, 2026Awais Khan, Muhammad Umar Farooq, Kutub Uddin +1Audio Deepfake Detection
College of Innovation and Technology, University of Michigan-Flint, MI, USA
Split and Conquer Partial Deepfake Speech
Apr 3, 2026Inbal Rimon, Oren Gal, Haim PermuterAudio Deepfake Detection ASVspoof
Ben Gurion University, Be’er Sheva, Israel · University of Haifa, Haifa, Israel
PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditions
Jul 11, 2026Zhenshan Zhang, Xueping Zhang, Linxi Li +2Audio Deepfake Detection Audio Classification
Digital Innovation Research Center, Duke Kunshan University, Kunshan, China · OfSpectrum, Inc., Los Angeles, USA · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China

Apr 1, 2026J/K move · Enter open · S save

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

Awais Khan, Muhammad Umar Farooq, Kutub Uddin, Khalid Malik

College of Innovation and Technology, University of Michigan-Flint, MI, USA

Audio Deepfake Detection

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

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

Split and Conquer Partial Deepfake Speech

PC-Mix: Partial-Component Audio Spoofing Detection under Mixed Speech and Environmental Sound Conditions