MixFake is a new benchmark for mixed-authenticity audio and a multi-stream prompt tuning method achieves 0.95% EER foreground and 7.72% absolute gain in complex background deepfake detection.
hub
XLS-R: Self-supervised cross-lingual speech represen- tation learning at scale
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
representative citing papers
MARS is a transfer-based black-box attack that uses bi-level optimization on semantic and artifact anchors to escape the linearity trap and improve attack success rates on SSL-SVDD by up to 36%.
PVP models speaker-specific phoneme acoustic distributions with lightweight GMMs trained only on real speech to detect deepfakes of persons-of-interest, outperforming generic detectors and introducing a new Chinese POI dataset.
Multilingual ASR models show 39.7-297% zero-shot WER on Pashto public data, Whisper models output correct script in under 0.8% of cases, and fine-tuned models degrade to 32.5-59% WER on out-of-domain sets.
Spoof-SUPERB benchmark shows large-scale discriminative SSL models such as XLS-R, UniSpeech-SAT, and WavLM Large outperform others in audio deepfake detection and maintain robustness under acoustic degradations.
Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
Linear probes on frozen self-supervised representations closely approach bespoke deepfake detector performance on benchmarks, indicating benchmarks largely measure general modality understanding.
A gated fusion of XLSR-53 and CORES features with energy margin and diversity losses reaches 97.6% ID accuracy and reduces FPR95 by 83.5% relative to the Interspeech 2025 baseline on MLAAD.
Introduces forensic similarity for speech deepfakes via a Siamese feature extractor and similarity network to verify shared forensic traces and source models between audio segments.
KEYAC dataset benchmarks speech models for keyboard acoustic side-channel attacks, with KAN fine-tuning setting new SOTA by addressing nonlinear feature interactions.
A framework using native-only trained discrete token surprisal and DTW alignment features improves pronunciation assessment PCC to 0.66 on SpeechOcean762, approaching supervised performance.
Truncated SSL backbone with logistic classifier detects audio deepfakes on-device, claimed to outperform AASIST by 10% while running 40% faster, packaged as a browser plugin.
Fine-tuned MMS model reaches 9.48% WER on Fongbe benchmark while Whisper on Hausa videos yields 6,770 segments rated 57.4/100 quality, with Fongbe lower at 36.5/100.
Benchmarks on the new FROST-EMA corpus show cross-language mismatch drops Pearson correlation by 0.10-0.20 while cross-gender mismatch drops it by 0.05-0.10.
Fine-tuned Wav2Vec2 and HuBERT models recognize click consonants more accurately than non-clicks in G|ui and West !Xoon data.
Cosine similarity in SupCon with a delayed negative queue on wav2vec2 XLS-R yields the lowest equal error rates for deepfake audio detection on in-the-wild and pooled evaluations.
A bilingual TTS system for the Peruvian Constitution in Quechua and Spanish is developed with XTTS v2, F5-TTS, and DiFlow-TTS, releasing checkpoints and audio to support low-resource speech synthesis.
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
Evaluation of open-source and commercial ASR models on narrow-band Hindi and Indian English shows poor zero-shot results and inconsistent fine-tuning benefits tied to pretraining exposure.
SpAArSIST sparsifies AASIST by swapping learned pooling for explicit magnitude-based scoring and mean aggregation, cutting compute 20.7% and improving In-the-Wild EER to 2.82%.
citing papers explorer
-
MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio
MixFake is a new benchmark for mixed-authenticity audio and a multi-stream prompt tuning method achieves 0.95% EER foreground and 7.72% absolute gain in complex background deepfake detection.
-
Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection
MARS is a transfer-based black-box attack that uses bi-level optimization on semantic and artifact anchors to escape the linearity trap and improve attack success rates on SSL-SVDD by up to 36%.
-
Profiling the Voice: Speaker-Specific Phoneme Fingerprinting for Speech Deepfake Detection
PVP models speaker-specific phoneme acoustic distributions with lightweight GMMs trained only on real speech to detect deepfakes of persons-of-interest, outperforming generic detectors and introducing a new Chinese POI dataset.
-
Benchmarking Multilingual Speech Models on Pashto: Zero-Shot ASR, Script Failure, and Cross-Domain Evaluation
Multilingual ASR models show 39.7-297% zero-shot WER on Pashto public data, Whisper models output correct script in under 0.8% of cases, and fine-tuned models degrade to 32.5-59% WER on out-of-domain sets.
-
A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection
Spoof-SUPERB benchmark shows large-scale discriminative SSL models such as XLS-R, UniSpeech-SAT, and WavLM Large outperform others in audio deepfake detection and maintain robustness under acoustic degradations.
-
Syntactic Belief Update as the Driver of Garden Path Processing Difficulty
Syntactic belief update via generalized Rényi divergence on syntactic trees predicts garden path reading times better than lexical surprisal.
-
What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations
Linear probes on frozen self-supervised representations closely approach bespoke deepfake detector performance on benchmarks, indicating benchmarks largely measure general modality understanding.
-
Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing
A gated fusion of XLSR-53 and CORES features with energy margin and diversity losses reaches 97.6% ID accuracy and reduces FPR95 by 83.5% relative to the Interspeech 2025 baseline on MLAAD.
-
Forensic Similarity for Speech Deepfakes
Introduces forensic similarity for speech deepfakes via a Siamese feature extractor and similarity network to verify shared forensic traces and source models between audio segments.
-
Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack
KEYAC dataset benchmarks speech models for keyboard acoustic side-channel attacks, with KAN fine-tuning setting new SOTA by addressing nonlinear feature interactions.
-
Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal
A framework using native-only trained discrete token surprisal and DTW alignment features improves pronunciation assessment PCC to 0.66 on SpeechOcean762, approaching supervised performance.
-
Detecting Audio Deepfakes on the Edge:Lightweight SSL-Based Detection in a Browser Plugin
Truncated SSL backbone with logistic classifier detects audio deepfakes on-device, claimed to outperform AASIST by 10% while running 40% faster, packaged as a browser plugin.
-
From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa
Fine-tuned MMS model reaches 9.48% WER on Fongbe benchmark while Whisper on Hausa videos yields 6,770 segments rated 57.4/100 quality, with Fongbe lower at 36.5/100.
-
Beyond Speaker Independence: Evaluating Cross-Lingual Acoustic-to-Articulatory Inversion Across Finnish and Russian
Benchmarks on the new FROST-EMA corpus show cross-language mismatch drops Pearson correlation by 0.10-0.20 while cross-gender mismatch drops it by 0.05-0.10.
-
Pretrained self-supervised speech models can recognize unseen consonants
Fine-tuned Wav2Vec2 and HuBERT models recognize click consonants more accurately than non-clicks in G|ui and West !Xoon data.
-
Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection
Cosine similarity in SupCon with a delayed negative queue on wav2vec2 XLS-R yields the lowest equal error rates for deepfake audio detection on in-the-wild and pooled evaluations.
-
Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus
A bilingual TTS system for the Peruvian Constitution in Quechua and Spanish is developed with XTTS v2, F5-TTS, and DiFlow-TTS, releasing checkpoints and audio to support low-resource speech synthesis.
-
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
-
Responsible ASR: Overcoming Challenges of Foundational Models in Narrow-Band and Low-Resource Settings
Evaluation of open-source and commercial ASR models on narrow-band Hindi and Indian English shows poor zero-shot results and inconsistent fine-tuning benefits tied to pretraining exposure.
-
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
SpAArSIST sparsifies AASIST by swapping learned pooling for explicit magnitude-based scoring and mean aggregation, cutting compute 20.7% and improving In-the-Wild EER to 2.82%.