RAST is a resolution‑aware transfer framework that addresses the mismatch between high‑resolution (HR) audio available during training and low‑resolution (LR) audio used at inference for human activity recognition. By compressing HR teacher representations while preserving token‑level information and neighborhood structure, RAST performs localized HR‑LR alignment. Experiments on the SAMoSA and AudioIMU datasets show that RAST consistently outperforms LR‑only training and direct teacher‑transfer baselines, improving LR‑only recognition by up to approximately 7.8% while requiring only LR audio at inference.
arXiv:2511. 20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.
arXiv:2606. 30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks.
HALO is a heterogeneity‑aware, language‑aligned foundation model for inertial measurement unit (IMU) based human activity recognition. It uses a two‑stage training process: first, a self‑supervised encoder learns to handle diverse sensor configurations and natural‑language sensor descriptions; second, the encoder is aligned with text embeddings through synonym‑aware contrastive learning, enabling open‑set recognition via cosine similarity. Trained on ten public HAR datasets, HALO outperforms five state‑of‑the‑art baselines across eight metrics while using only ~35 M parameters, and improves zero‑shot open‑set accuracy by 13.7 percentage points over 87 training labels.
UniAE-MoE is a unified audio encoder that uses a Mixture-of-Experts architecture to model cross‑domain audio representations. It integrates encoder components from Qwen2‑Audio and Audio‑Flamingo 3, enhances them with SwiGLU and shared experts, and applies a two‑stage instruction‑tuning strategy along with task‑specific data scaling. The model achieves state‑of‑the‑art results on the XARES‑LLM benchmark (0.802) and tops the Interspeech 2026 Audio Encoder Capability Challenge, demonstrating strong generalization across speech, music, and general audio tasks.
arXiv:2606. 11922v1 Announce Type: cross Abstract: Recent respiratory sound classification (RSC) studies largely rely on CLS-token driven self-attention architectures such as the Audio Spectrogram Transformer (AST).
arXiv:2607. 26631v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments.
arXiv:2602. 10230v2 Announce Type: replace Abstract: Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding.
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
arXiv:2609.36577v1 Announce Type: cross Abstract: Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks. However, these capabilities usually co...
arXiv:2608. 19863v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate pre-training recipes to reach competitive performance.
TEMPO is a unified model that adds temporally‑grounded capabilities to large audio‑language models, enabling timestamping of events, speakers, and sounds in audio, speech, and music. It introduces a supervised fine‑tuning stage featuring atomic timestamp tokens, a time‑aware projector with sinusoidal encodings, and a distance‑aware Gaussian loss, trained via a synthetic‑to‑real curriculum. Additionally, TEMPO employs reinforcement learning (GRPO) as a refinement step, and achieves state‑of‑the‑art performance on a benchmark of 10K samples across five timestamping tasks, surpassing Audio Flamingo Next and Qwen3‑Omni.
arXiv:2606. 04106v1 Announce Type: cross Abstract: Foundation models achieve generalization through massive-scale training on diverse data, but have limitations with transfer to truly unseen domains without paired training data.