arXiv:2603. 27998v2 Announce Type: replace-cross Abstract: Individualized head-related impulse responses (HRIRs) enable binaural rendering, but dense per-listener measurements are costly.
arXiv:2510. 01891v2 Announce Type: replace-cross Abstract: Individual Head-Related Transfer Functions (HRTFs) are starting to be introduced in many commercial immersive audio applications and are crucial for realistic spatial audio rendering.
NeuroCodec is a novel generative framework that uses EEG signals to guide target speaker extraction in multi‑talker environments. It operates in the latent space of a neural audio codec, modeling EEG spatial dependencies with graph convolutions and fusing EEG and speech representations via attention and Mamba‑based temporal modeling. A six‑phase training curriculum and a causal streaming version enable high‑fidelity, 44.1 kHz audio reconstruction up to 20 kHz, outperforming baselines on Cocktail Party and KUL datasets and receiving higher perceptual scores in a listening test.
arXiv:2511. 05350v3 Announce Type: replace-cross Abstract: We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptually motivated losses, yields encodings that are structured according to a perceptual hierarchy.
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...
The paper investigates token sparsification for audio transformers, evaluating various pruning and merging methods across multiple datasets and model sizes. It introduces a new approach that blends attention scores with spectral cues from token embeddings, showing that frequency-aware techniques outperform attention-only methods. The study finds that spectrogram patch intensity-based sparsification is particularly effective for longer audio inputs, underscoring the benefit of incorporating frequency-domain information into sparsification strategies.
AudioTETRIS is a training‑free, two‑stage token elimination framework designed for large audio language models. It leverages the geometry of audio encoder representations as an acoustic prior to compute per‑token importance scores, which guide progressive top‑k token selection across decoder layers. Experiments on Qwen2‑Audio‑7B, Phi‑4‑Multimodal, and Audio Flamingo 3 show that AudioTETRIS retains near‑full performance while using only 25% of audio tokens and outperforms existing training‑free baselines.
arXiv:2610.07419v1 Announce Type: new Abstract: Implicit neural representations (INRs) are shaped by the spectral structure induced by their input encodings and activation functions. Existing methods...
Mizar is a 159.3‑million‑parameter audio‑language model designed for devices with limited memory and computation. It couples a compact CED‑Small audio encoder with SmolLM2‑135M via a frequency‑merging mapper and is trained in three stages—audio‑language alignment, audio‑dependent fine‑tuning, and post‑training—to improve performance on audio‑question tasks. Across five random seeds, Mizar outperforms all other sub‑200M‑parameter ALMs on MMAU, MMAR, and ADQA‑clean, achieving mean accuracies of 52.92%, 42.42%, and 36.02% respectively, while enabling local inference on a single CPU with an average latency of 1.09 seconds for MMAU questions.
arXiv:2610.17131v2 Announce Type: cross Abstract: Dynamic spatial audio reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at...
AudioWorldSim is an open‑source platform that generates realistic binaural audio datasets for training and evaluating audio‑based machine learning models, especially world models. It extends Meta’s SoundSpaces 2.0 by automating random agent navigation and correcting continuous sound composition. The project is publicly available on GitHub to support reproducibility in research.
arXiv:2607. 00247v1 Announce Type: cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors.