cs.SDNov 9, 2026

Which Acoustic Features Survive Compression? Tracker-Estimated First-Formant Statistics for Codec-Robust Audio DeepfakeDetection

Authors: Yash Sukhdeve, Aaron Storey, Masudul H. Imtiaz

Organizations: Department of Electrical and Computer Engineering, Clarkson University, Potsdam, NY 13699, USA · Department of Computer Science, Clarkson University, Potsdam, NY 13699, USA

Abstract

Audio deepfake detectors that work well on clean lab recordings often degrade after telephone or platform compression. This paper asks a specific question: which low-dimensional acoustic descriptors stay informative after codec degradation? We screen 36 utterance-level features(formants, PNCCs, LFCCs, prosody) on ASVspoof 2019 data and test on the official ASVspoof 2021 LA set across seven codec conditions. Of 33 statistically significant descriptors, only four show large practical separation (|r| >0.5, bootstrap 95% CIs), all first-formant (F1) measures, highly redundant (PC1: 79% variance). The payoff is stability: the 36-feature SVM degrades 14 pp under codec mismatch (9.5%-23.5% EER), while the four-feature RBF-SVM degrades only 5.9 pp (17.0%-22.9%). The F1 subset varies 3.4 pp across conditions versus 13.1 pp for the full set. F1 differences persist after controlling for speaker identity (p greater than 10^10, mixed-effects model). The results suggest that physically interpretable F1 statistics offer a compact, codec-stable diagnostic signal that may complement higher accuracy neural detectors.

Figures & tables

Explore similar work

CardsList
  1. Neural Audio Codec for Robust Audio Deepfake Detection

    Sep 30, 2026Jungwoo Kim, Joonyong Park, Junyoung Koh +1Neural Audio CodecsAudio Deepfake Detection

  2. Exposing and Mitigating Neural Codec Vulnerabilities in Audio Deepfake Detection

    Oct 5, 2026Abdullah, Awais Khan, Khalid Mahmood MalikNeural Audio CodecsAudio Deepfake Detection

  3. What Survives the Codec Shift: Pooled No-Vocals Residuals for Speech Deepfake Detection

    Sep 27, 2026Jiajun Xu, Menglu Li, Xiao-Ping ZhangAudio Representation LearningAudio Deepfake Detection