Papers for

audio forensics analysts

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

WavLM layers reveal how speech models detect fake audio attacks

Interpreting SSL Representations for Spoof Detection: a WavLM Study

Abstract: Self-supervised speech models such as WavLM achieve strong spoofing detection performance, yet which layers encode the most spoof-relevant information and what acoustic properties they capture remain opaque. We present a layer-wise interpretability study of WavLM using the ASVspoof 5 database, combining three complementary analyses: (i) per-layer linear probing with attack-level evaluation across speech synthesis, voice conversion, and adversarial attacks; (ii) a canonical correlation analysis (CCA) linking layer representations to spoofing-relevant acoustic features; (iii) an exhaustive grid search over layer subsets showing that use of five layers outperforms full thirteen-layer pooling. CCA analysis reveals that, while most acoustic features peak in alignment with mid-layers and then decay, voice quality measures jitter, shimmer, and the harmonics-to-noise ratio show the opposite trend, with correlation increasing toward later layers. Embedding visualisations reveal that deeper layers capture a continuous acoustic similarity among attacks rather than discrete categories, suggesting these layers encode fundamental synthesis artifacts rather than attack-specific signatures.

Fri 16 OctSoundMachine Learning
The gist
Detecting fake or spoofed speech is important for security, but it's unclear how self-supervised speech models like WavLM do it. The authors studied which layers of WavLM best detect various fake speech attacks and what sound features they focus on. They found mid layers capture general audio traits while later layers detect signs related to voice quality. These deeper layers don’t just spot specific attacks but recognize subtle artifacts common across different types of fakes.
Open → 2610.23526v1

Deepfake audio detectors rely more on events than speech sounds

What Do Deepfake Audio Detectors Hear? From Self-Supervised Models to Audio LLMs

Abstract: Real-world audio recordings for deepfake detection rarely consist solely of speech; they often are mixtures of speech and background events that themselves may also be synthetic. When processing these mixtures, it remains unclear whether detectors attend to the speech or the background event, and where their spectral evidence lies. We study this on the CompSpoof V2 database, whose mixtures pair independently real-or-fake speech and event components. Our results show that all systems detect fake events more accurately than fake speech. However, this performance gap is largely driven by poor generalization to an unseen fake speech domain, rather than a true difference in difficulty. Furthermore, sub-band probing reveals that the front-end encoder dictates where a countermeasure focuses its frequency evidence. To enable reliable deployment in real-world scenarios, future countermeasures should address out-of-domain generalization failures and carefully select front-end encoders aligned with their target acoustic evidence. Our source code and checkpoints are released at https://github.com/nii-yamagishilab/AntiDeepfake-AudioLLM.

Tue 13 OctSound
The gist
Detecting fake audio is tricky because real recordings usually mix speech with background noises, and both can be faked. The authors studied how well detectors spot fake speech versus fake background sounds and found detectors identify fake background noises better than fake speech. However, this difference is due to detectors struggling with new types of fake speech they haven't seen before, not because fake speech is inherently harder to detect. They also discovered the part of the detector that processes sound waves strongly influences which frequencies it focuses on. To improve fake audio detection, future tools need to handle unfamiliar fake speech better and choose their sound-processing methods carefully.
Open → 2610.17617v1