NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating

• URL: http://arxiv.org/abs/2605.13651v1
• Date: Wed, 13 May 2026 15:09:47 GMT
• Title: NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating
• Abstract summary: We introduce NAACA, a training-free NeuroAuditory Attentive Cognitive Architecture that reframes attention allocation as an auditory salience problem.<n>OWM is a neuro-inspiredy Working Memory that maintains stable attractor-like states and triggers higher-cognition ALM processing.
• Score: 6.273703979947789
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free NeuroAuditory Attentive Cognitive Architecture that reframes attention allocation as an auditory salience filtering problem. At its core is OWM, a neuro-inspired Oscillatory Working Memory that maintains stable attractor-like states and triggers higher-cognition ALM processing only when adaptive energy fluctuations signal perceptual salience, triggering higher-level reasoning. On XD-Violence, NAACA improves AudioQwen's average precision (AP) from 53.50% to 70.60% while reducing unnecessary ALM invocations. Furthermore, qualitative case studies on the Urban Soundscapes of the World (USoW) dataset show that OWM captures novel events and subcategory shifts while remaining robust to transient pauses and ambient urban noise.

Related papers

• iBrain: A Unified Foundation Model Reading the Brain from Surface to Spikes [3.2517081185249075]
  We introduce iBrain, a unified foundation model that jointly learns from iEEG and spiking activity.<n>We pretrain iBrain on over 7,000 hours of heterogeneous neural recordings using masked signal reconstruction and channel-view alignment.<n>iBrain consistently outperforms single-signal pretraining baselines and achieves state-of-the-art performance on multiple benchmarks.
  arXiv  Detail & Related papers  (2026-09-07T02:56:42Z)
• Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech [1.497166779417398]
  Non-invasive brain-to-speech decoding aims to restore communication to patients suffering from neurodegenerative disease.<n>Existing MEG- and EEG-based methods, while scalable, continue to suffer from high word error rates driven by relatively low signal-to-noise ratios.<n>We propose physiological noise augmentation (PNA), a data augmentation method that explicitly trains decoders to become invariant to task-agnostic artifacts.
  arXiv  Detail & Related papers  (2026-07-06T14:47:31Z)
• See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs [81.71384150441163]
  We propose Context-aware Attention Intervention (CAI) for large vision-language models (LVLMs)<n>CAI enforces a see only when needed principle via two-axis selectivity: where to look and when to intervene.<n> experiments across multiple LVLM backbones and benchmarks show that CAI achieves state-of-the-art hallucination mitigation.
  arXiv  Detail & Related papers  (2026-06-29T06:35:47Z)
• In Silico Modeling of the RAMPHO Buffer: Dissociating Informational and Energetic Masking via Phonetic Entropy in Deep Neural Networks [0.0]
  We present an in silico simulation of the RAMPHO buffer using the frame-by-frame phonetic entropy of a self-supervised acoustic model (wav2vec 2.0)<n>By contrasting a semantically intact distractor with a phase-decorrelated distractor, we successfully dissociate the cognitive penalty of informational distraction from the physical penalty of energetic decay.<n>The simulation reveals a cognitive-acoustic optimization problem: destroying a distractor's semantic payload provides a release from informational masking at high SNRs, but fundamentally degrades temporal glimpsing cues at low SNRs.
  arXiv  Detail & Related papers  (2026-05-21T13:25:28Z)
• Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps [1.8825446478246406]
  Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods rely on gold-standard outputs that are costly or impractical to obtain.<n>We investigate four attention-derived metrics: AUDIORATIO, AUDIOCONSISTENCY, AUDIOENTROPY, and TEXTENTROPY, designed to capture pathological attention patterns associated with hallucination.<n>Across automatic speech recognition and speech-to-text translation tasks, our approach outperforms uncertainty-based and prior attention-based baselines.
  arXiv  Detail & Related papers  (2026-04-21T15:18:10Z)
• MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation [59.709198999959206]
  Speech-based automatic estimation of depression levels is essential for enabling early detection and timely intervention.<n>Most existing approaches rely on RNN-based architectures to model temporal information for depression estimation.<n>We introduce a memory-based feature augmentation method that enhances the representational capacity of GRU-extracted features.
  arXiv  Detail & Related papers  (2026-04-20T14:42:13Z)
• NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition [17.96933456290729]
  Lip motion encodes subject-specific behavioral dynamics driven by consistent articulation patterns and muscle coordination.<n>NeuroLip is an event-based framework that captures fine-grained lip dynamics under a strict yet practical cross-scene protocol.<n>NeuroLip achieves near-perfect matched-scene accuracy and robust cross-scene recognition, attaining over 71% accuracy on unseen viewpoints.
  arXiv  Detail & Related papers  (2026-04-17T05:42:17Z)
• Neuro-RIT: Neuron-Guided Instruction Tuning for Robust Retrieval-Augmented Language Model [18.49378483853084]
  Neuro-RIT (Neuron-guided Robust Instruction Tuning) is a novel framework that shifts the paradigm from dense adaptation to precision-driven neuron alignment.<n>Our method explicitly disentangles neurons that are responsible for processing relevant versus irrelevant contexts using attribution-based neuron mining.
  arXiv  Detail & Related papers  (2026-04-02T15:49:50Z)
• SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation [33.381194425912234]
  Large vision-language models (VLMs) frequently suffer from hallucinations, generating content that is inconsistent with visual inputs.<n>We introduce SAGE, a Sink-Aware Grounded Decoding framework that mitigates hallucinations by dynamically modulating self-attention during generation.<n>Our method achieves an average relative improvement of 10.65% on MSCOCO and 7.19% on AMBER across diverse VLM architectures.
  arXiv  Detail & Related papers  (2026-03-29T22:52:03Z)
• Neural Dynamics Self-Attention for Spiking Transformers [59.57278823240336]
  Spiking Neural Networks (SNNs) with Transformer architectures offer a promising pathway to balance energy efficiency and performance.<n>Existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference.<n>We propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements.
  arXiv  Detail & Related papers  (2026-03-09T12:23:37Z)
• How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime? [78.0226274470175]
  We investigate whether introducing label noise to the gradient updates can enhance the test performance of neural network (NN)<n>We prove that adding label noise during training suppresses noise memorization, preventing it from dominating the learning process.<n>In contrast, we show that NN trained with standard GD tends to overfit to noise in the same low SNR setting.
  arXiv  Detail & Related papers  (2025-10-20T13:28:13Z)
• WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations [67.6147632074449]
  We introduce the World-of-Whale benchmark (WoW-Bench) to evaluate low-level auditory perception and cognition using marine mammal vocalizations.<n>WoW-Bench is composed of a Perception benchmark for categorizing novel sounds and a Cognition benchmark, inspired by Bloom's taxonomy, to assess the abilities to remember, understand, apply, and analyze sound events.<n>Experiments with state-of-the-art LALMs show performance far below human levels, indicating a need for stronger auditory grounding in LALMs.
  arXiv  Detail & Related papers  (2025-08-28T16:29:46Z)
• Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields [61.07542274267568]
  This letter proposes a novel Neural Acoustic Context Field approach, called NACF, to parameterize an audio scene. Driven by the unique properties of RIR, we design a temporal correlation module and multi-scale energy decay criterion. Experimental results show that NACF outperforms existing field-based methods by a notable margin.
  arXiv  Detail & Related papers  (2023-09-27T19:50:50Z)
• Spiking-LEAF: A Learnable Auditory front-end for Spiking Neural Networks [53.31894108974566]
  Spiking-LEAF is a learnable auditory front-end meticulously designed for SNN-based speech processing. On keyword spotting and speaker identification tasks, the proposed Spiking-LEAF outperforms both SOTA spiking auditory front-ends.
  arXiv  Detail & Related papers  (2023-09-18T04:03:05Z)
• When Noise meets Chaos: Stochastic Resonance in Neurochaos Learning [0.0]
  We demonstrate Resonance (SR) phenomenon in Neurochaos Learning (NL) SR manifests at the level of a single neuron of NL and enables efficient subthreshold signal detection. Intermediate levels of noise in neurochaos learning enables peak performance in classification tasks.
  arXiv  Detail & Related papers  (2021-02-02T05:16:55Z)

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.