A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning

• URL: http://arxiv.org/abs/2603.26098v1
• Date: Fri, 27 Mar 2026 06:09:03 GMT
• Title: A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning
• Abstract summary: We propose HEAR (Human-inspired Efficient Audio Representation), a novel decoupled architecture.<n>HEAR splits the processing pipeline into two dedicated modules: an Acoustic Model for local feature extraction and a Task Model for global semantic integration.<n>Experiments demonstrate that HEAR requires only 15M parameters and 9.47 GFLOPs for inference, operating at a fraction of the computational cost of conventional foundation models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While self-supervised learning (SSL) has revolutionized audio representation, the excessive parameterization and quadratic computational cost of standard Transformers limit their deployment on resource-constrained devices. To address this bottleneck, we propose HEAR (Human-inspired Efficient Audio Representation), a novel decoupled architecture. Inspired by the human cognitive ability to isolate local acoustic features from global context, HEAR splits the processing pipeline into two dedicated modules: an Acoustic Model for local feature extraction and a Task Model for global semantic integration. Coupled with an Acoustic Tokenizer trained via knowledge distillation, our approach enables robust Masked Audio Modeling (MAM). Extensive experiments demonstrate that HEAR requires only 15M parameters and 9.47 GFLOPs for inference, operating at a fraction of the computational cost of conventional foundation models (which typically require 85M-94M parameters). Despite this high efficiency, HEAR achieves highly competitive performance across diverse audio classification benchmarks. The code and pre-trained models are available at https://github.com/HarunoriKawano/HEAR

Related papers

• AudioMosaic: Contrastive Masked Audio Representation Learning [53.52371029884106]
  We introduce textbfAudioMosaic, a contrastive learning-based audio encoder for general audio understanding.<n>AudioMosaic constructs positive pairs by applying structured time-frequency masking to spectrogram patches.<n>Experiments show that AudioMosaic achieves state-of-the-art performance on several standard audio benchmarks.
  arXiv  Detail & Related papers  (2026-05-14T00:56:51Z)
• Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs [53.41256816230278]
  Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion.<n>While excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception.<n>We propose Unified Audio (UAS), a holistic and structured supervision framework that organizes audio information into three explicit components.
  arXiv  Detail & Related papers  (2026-04-14T09:30:12Z)
• Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens [62.56027815951259]
  Current audio language models are predominantly text-first, either extending pre-trained text LLM backbones or relying on semantic-only audio tokens.<n>This paper presents a systematic empirical study of native audio foundation models that apply next-token prediction to audio at scale.
  arXiv  Detail & Related papers  (2026-02-18T18:32:46Z)
• DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding [58.29124051111574]
  We introduce DIFFA-2, a practical diffusion-based LALM for general audio understanding.<n>DIFFA-2 upgrades the speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum.<n>Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA.
  arXiv  Detail & Related papers  (2026-01-30T16:44:23Z)
• Representation-Regularized Convolutional Audio Transformer for Audio Understanding [53.092757178419355]
  bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge.<n>We propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2026-01-29T12:16:19Z)
• The OCON model: an old but green solution for distributable supervised classification for acoustic monitoring in smart cities [0.28675177318965045]
  This paper focuses on vowel phonemes classification and speakers recognition for the Automatic Speech Recognition domain. For our case-study, the ASR model runs on a proprietary sensing and lightning system, exploited to monitor acoustic and air pollution on urban streets. We formalize combinations of pseudo-Neural Architecture Search and Hyper-s Tuning experiments, using an informed grid-search methodology, to achieve classification accuracy comparable to nowadays most complex architectures.
  arXiv  Detail & Related papers  (2024-10-05T09:47:54Z)
• Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model [35.171785986428425]
  We propose Audio-Visual Lightweight ITerative model (AVLIT) to perform audio-visual speech separation in noisy environments. Our architecture consists of an audio branch and a video branch, with iterative A-FRCNN blocks sharing weights for each modality. Experiments demonstrate the superiority of our model in both settings with respect to various audio-only and audio-visual baselines.
  arXiv  Detail & Related papers  (2023-05-31T20:09:50Z)
• MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training [74.32603591331718]
  We propose an acoustic Music undERstanding model with large-scale self-supervised Training (MERT), which incorporates teacher models to provide pseudo labels in the masked language modelling (MLM) style acoustic pre-training.<n> Experimental results indicate that our model can generalise and perform well on 14 music understanding tasks and attain state-of-the-art (SOTA) overall scores.
  arXiv  Detail & Related papers  (2023-05-31T18:27:43Z)
• A Light Weight Model for Active Speaker Detection [7.253335671577093]
  We construct a lightweight active speaker detection architecture by reducing input candidates, splitting 2D and 3D convolutions for audio-visual feature extraction, and applying gated recurrent unit (GRU) with low computational complexity for cross-modal modeling. Experimental results on the AVA-ActiveSpeaker dataset show that our framework achieves competitive mAP performance (94.1% vs. 94.2%). Our framework also performs well on the Columbia dataset showing good robustness.
  arXiv  Detail & Related papers  (2023-03-08T08:40:56Z)
• Continual Learning for On-Device Speech Recognition using Disentangled Conformers [54.32320258055716]
  We introduce a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks. We propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR.
  arXiv  Detail & Related papers  (2022-12-02T18:58:51Z)
• Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition [9.732767611907068]
  In this work, we fuse a pre-trained acoustic encoder (wav2vec2.0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model. Our model achieves better recognition performance on CALLHOME corpus (15 hours) than other end-to-end models.
  arXiv  Detail & Related papers  (2021-01-17T16:12:44Z)

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.