CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection

• URL: http://arxiv.org/abs/2609.13842v1
• Date: Sat, 12 Sep 2026 09:56:45 GMT
• Title: CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection
• Abstract summary: Speech and audio models offer a promising direction for improving robustness to such unseen attacks.<n>We propose CRAF, a cross-view residual-aware fusion framework.<n>We show that CRAF with Kimi-Audio achieves an EER of 5.96% and a minDCF of 0.1192, demonstrating robustness to unseen spoofing attacks.
• Score: 5.977697197923706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in speech synthesis and voice conversion have made deepfake speech increasingly realistic, making generalization to unseen spoofing attacks a critical challenge. Pretrained speech and audio models offer a promising direction for improving robustness to such unseen attacks. Self-supervised learning (SSL) models capture fine-grained, low-level acoustic characteristics, whereas Auditory Large Language Models (ALLMs) provide higher-level contextual representations. These complementary views can provide useful cues for improving generalization to unseen attacks. However, direct fusion does not explicitly disentangle information shared across the two views from view-specific complementary information, limiting effective cross-view integration. To address this, we propose CRAF, a cross-view residual-aware fusion framework that uses ALLM-guided cross-view attention to enrich SSL representations and adopts ALLM as a high-level reference to separate ALLM-explainable information from complementary SSL residual information. The residual is selectively refined through adaptive gating and integrated through SSL-primary fusion. Experiments on ASVspoof 5 show that CRAF with Kimi-Audio achieves an EER of 5.96% and a minDCF of 0.1192, demonstrating robustness to unseen spoofing attacks.

Related papers

• Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions [120.64235456332916]
  Speech recognition systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge.<n>We refine warm-adapted LLM-based ASR models by leveraging their own pre-adaptation base LLMs.<n>We propose Hybrid Search, a targeted correction strategy motivated by two observations.
  arXiv  Detail & Related papers  (2026-08-31T15:46:48Z)
• DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation [4.041253468990907]
  We present DAVE, a decoupled audio-visual enhancement framework for real-world speech separation.<n>To address the data scarcity issue, we construct DAVE-Corpus, a large-scale training corpus with 219,411 mixtures generated from public meeting corpora.<n>We further develop a certified selective enhancement chain that applies scene routing, GAN-based denoising, and loudness normalization only within the no-reference partition.
  arXiv  Detail & Related papers  (2026-08-10T08:41:28Z)
• Listening Between the Lines: Joint Learning of ASR Embeddings and LLM-Augmented Linguistics for Dementia Detection [3.4155322317700585]
  Early detection of dementia through speech analysis offers a non-invasive screening alternative, but capturing both acoustic and linguistic biomarkers remains challenging.<n>We propose a multimodal framework leveraging Whisper for dual-purpose extraction: acoustic representations from encoder outputs and transcripts via automatic speech recognition (ASR)<n>For the acoustic pathway, temporal networks with attention pooling aggregate variable-length sequences into fixed-dimensional embeddings.<n>For the linguistic pathway, we prompt a large language model (LLM) to extract interpretable features spanning lexical diversity, syntactic complexity, semantic coherence, and discourse patterns.
  arXiv  Detail & Related papers  (2026-06-26T08:21:31Z)
• Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection [22.306688903148046]
  Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text.<n>We propose textitAudioHijack, a framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs.<n>Experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 categories misbehavior.
  arXiv  Detail & Related papers  (2026-04-16T04:22:11Z)
• ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration [71.21097024566285]
  Large-Language Models (LVLMs) frequently suffer from severe hallucination issues.<n>Existing mitigation strategies rely on linguistic, single-step states to enhance visual focus or suppress strong priors.<n>We propose Adaptive Context in VisionTegration (ACT), a training-free inference intervention method that mitigates hallucination through the adaptive integration of contextual information.
  arXiv  Detail & Related papers  (2026-04-01T14:49:50Z)
• Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation [51.743225614196774]
  Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning.<n>They remain vulnerable to hallucination, where generated content deviates from visual evidence.<n>Recent vision enhancement methods attempt to address this issue by reinforcing visual tokens during decoding.<n>We propose Adaptive Visual Reinforcement (AIR), a training-free framework for MLLMs.
  arXiv  Detail & Related papers  (2026-02-27T14:18:51Z)
• Training-Free Intelligibility-Guided Observation Addition for Noisy ASR [57.74127683005929]
  This paper proposes an intelligibility-guided observation addition (OA) method to improve speech recognition in noisy environments.<n>Experiments across diverse SE-ASR combinations and datasets demonstrate strong robustness and improvements over existing OA baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:46:54Z)
• Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection [11.121265242990166]
  Recent advances in synthetic speech have made audio deepfakes increasingly realistic, posing significant security risks.<n>Existing detection methods that rely on a single modality, either raw waveform embeddings or spectral based features, are vulnerable to non spoof disturbances.<n>We investigate hybrid fusion frameworks that integrate self supervised learning (SSL) based representations with handcrafted spectral descriptors.
  arXiv  Detail & Related papers  (2025-07-27T21:22:27Z)
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition [70.77292069313154]
  Large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF)
  arXiv  Detail & Related papers  (2024-02-08T07:21:45Z)
• Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation [83.36685075570232]
  This work provides an insightful investigation of speech separation in reverberant and noisy-reverberant scenarios as an ASR front-end. We explore multi-channel separation methods, mask-based beamforming and complex spectral mapping, as well as the best features to use in the ASR back-end model. A proposed integration using TF-GridNet-based complex spectral mapping and WavLM-based SSLR achieves a 2.5% word error rate in reverberant WHAMR! test set.
  arXiv  Detail & Related papers  (2023-07-23T05:39:39Z)
• The effectiveness of unsupervised subword modeling with autoregressive and cross-lingual phone-aware networks [36.24509775775634]
  We propose a two-stage learning framework that combines self-supervised learning and cross-lingual knowledge transfer. Experiments on the ABX subword discriminability task conducted with the Libri-light and ZeroSpeech 2017 databases showed that our approach is competitive or superior to state-of-the-art studies.
  arXiv  Detail & Related papers  (2020-12-17T12:33:49Z)

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.