REIMU: Efficient Heterogeneous Hierarchical Reasoning for SSL-Based Speech Deepfake Detection

• URL: http://arxiv.org/abs/2608.00857v1
• Date: Sat, 01 Aug 2026 20:32:46 GMT
• Title: REIMU: Efficient Heterogeneous Hierarchical Reasoning for SSL-Based Speech Deepfake Detection
• Abstract summary: Self-supervised learning (SSL) has substantially advanced speech deepfake detection.<n>This work investigates the practical effectiveness of recurrent hierarchical reasoning for this task.
• Score: 6.6933354669653236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The increasing realism of speech generated by text-to-speech and voice conversion systems poses growing challenges to media integrity and voice authentication. Self-supervised learning (SSL) has substantially advanced speech deepfake detection, where downstream backbones conventionally process SSL representations through a single forward pass. This work investigates the practical effectiveness of recurrent hierarchical reasoning for this task. We term this controlled study REIMU and systematically compare conventional single-pass backbones, weight-shared recurrence, homogeneous HRM, and heterogeneous HRM across four Base-scale SSL frontends. We further examine heterogeneous high- and low-level modules that combine self-attention with linear attention. Experiments on the ASVspoof 2019 and 2021 evaluation sets show that recurrence and hierarchical decomposition do not inherently improve detection, whereas heterogeneous operator assignment provides a more competitive configuration. Notably, the heterogeneous design remains competitive while using 10.8\% fewer downstream parameters than the matched baseline, demonstrating its potential for parameter-efficient speech deepfake detection.

Related papers

• CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection [5.977697197923706]
  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.
  arXiv  Detail & Related papers  (2026-09-12T09:56:45Z)
• Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction [0.8749675983608171]
  cascaded multi-talker ASR (MT-ASR) performance is often capped by speaker leakage during separation.<n>We propose a complementary pruning-based paradigm that robustly identifies and removes leakage artifacts.<n>Results on LibriMix, LibriSpeechMix, and the AMI Meeting corpus show our algorithm consistently reduces cpW ER across diverse overlap conditions.
  arXiv  Detail & Related papers  (2026-08-23T03:21:45Z)
• Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection [0.0]
  We train a causal LSTM next-frame predictor on bonafide speech only.<n>System achieves competitive or state-of-the-art performance across six benchmarks.
  arXiv  Detail & Related papers  (2026-08-13T23:06:34Z)
• ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models [12.527207210862151]
  ReHear is a framework for iterative pseudo-label refinement in automatic speech recognition.<n>It integrates an instruction-tuned, audio-aware large language model into the self-training loop.<n>We show that ReHear effectively mitigates error propagation, consistently outperforming both supervised and pseudo-labeling baselines.
  arXiv  Detail & Related papers  (2026-02-21T05:04:22Z)
• Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses [71.34350093068473]
  This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR)<n>Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models.<n>Our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain.
  arXiv  Detail & Related papers  (2025-10-15T08:27:16Z)
• MARS-Sep: Multimodal-Aligned Reinforced Sound Separation [72.85468563236005]
  MARS-Sep is a reinforcement learning framework for sound separation.<n>It learns a factorized Beta mask policy that is optimized by a clipped trust-region surrogate.<n>Experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation.
  arXiv  Detail & Related papers  (2025-10-12T09:05:28Z)
• Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition [71.87998918300806]
  This paper explores approaches to integrate domain fine-tuned SSL pre-trained models and their features into TDNN and Conformer ASR systems. TDNN systems constructed by integrating domain-adapted HuBERT, wav2vec2-conformer or multi-lingual XLSR models consistently outperform standalone fine-tuned SSL pre-trained models. Consistent improvements in Alzheimer's Disease detection accuracy are also obtained using the DementiaBank Pitt elderly speech recognition outputs.
  arXiv  Detail & Related papers  (2024-07-03T08:33:39Z)
• Retrieval-Augmented Audio Deepfake Detection [27.13059118273849]
  We propose a retrieval-augmented detection framework that augments test samples with similar retrieved samples for enhanced detection. Experiments show the superior performance of the proposed RAD framework over baseline methods.
  arXiv  Detail & Related papers  (2024-04-22T05:46:40Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• 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)
• Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem [65.25725367771075]
  This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem. Specifically, we propose a novel speech separation/enhancement model based on the recognition of discrete symbols. By utilizing the synthesis model with the input of discrete symbols, after the prediction of discrete symbol sequence, each target speech could be re-synthesized.
  arXiv  Detail & Related papers  (2021-12-17T08:35:40Z)

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.