MADS (Multi-view Acoustic Descriptor Set) is a compact 19‑dimensional, physics‑informed descriptor set designed to capture spectral, temporal, mechanical, and stochastic aspects of audio signals. Unlike traditional log‑mel or MFCC representations, MADS encodes excitation, damping, periodicity, impulsiveness, and structural consistency in a unified multi‑view format. Evaluated on ESC‑10, ESC‑50, and MSoS datasets with classical machine learning models, MADS outperforms conventional 26‑D MFCC and 38‑D spectral‑summary baselines, achieving 81.00% on ESC‑10, 52.78% on ESC‑50, and 67.48% on MSoS while using roughly half the dimensionality of the 38‑D baseline.
By Utsab Ghosh, Roshni Chakraborty
Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. While highly successfu...
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).
By Hemansh Shridhar, Miika Toikkanen, June-Woo Kim
arXiv:2606. 27543v1 Announce Type: cross Abstract: The variations in vocal effort range (e.
By Zahra Omidi, John H. L. Hansen
arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.
By Maris Basha, Anja Zai, Sabine Stoll, Richard Hahnloser
SsgCaps is a publicly available dataset of human-engineered sound scenes, each paired with a precisely structured prompt that guides the sampling process. The prompts are drawn from a predefined action-based typology, enabling extensive yet plausible sampling. A comparative quantitative analysis shows only small differences between the open and private versions, supporting the recommendation of the open version for benchmarking sound scene generation algorithms.
By Modan Tailleur (LS2N), Junwon Lee (LS2N), Laurie M Heller (LS2N), Mathieu Lagrange (LS2N), Keunwoo Choi, Brian McFee, Keisuke Imoto, Yuki Okamoto
arXiv:2603. 02794v2 Announce Type: replace-cross Abstract: We present TVF (Time-Varying Filtering), an interpretable, low-latency speech enhancement model for real-time, on-device assistive hearing.
By Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff, Milos Cernak
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.
By Kaiyang Li, Shaobo Han, Yue Tian, Shihao Ji
arXiv:2607. 03806v1 Announce Type: cross Abstract: Audio foundation models are widely adopted as general-purpose feature extractors, yet the internal structure of their learned representations remains insufficiently understood.
By H\'ector Martel, Joe Hennessy-Priest, Taemin Cho
The study evaluates audio provenance attribution systems, showing that high clean‑benchmark accuracy does not translate to robustness after codec compression. Using a prospectively registered protocol, the authors measured closed‑set attribution performance on two corpora after single‑stage codec transport, finding significant degradation—up to 70.3 Macro‑F1 points for WavLM‑Base+ and 61.0 for W2V2‑BERT 2.0—depending on codec settings and representation. The results demonstrate that clean accuracy alone cannot guarantee deployment robustness across different codecs and representations.
By Gang Shi (Independent Researcher)
We benchmark eleven audio classification methods: five task-aware closed-set LLMs (four Gemini models plus open-weight Kimi-Audio-7B-Instruct), four fixed-vocabulary taggers (YAMNet, PANNs, Whisper-AT, and SSLAM), a zero-shot audio-text model (CLAP), and an audio-grounded LLM (BAT). We evaluate them on a closed-set sound-source identification task over 2,242 clips spanning 23 fine-grained classes and 11 categories.
arXiv:2606. 30700v1 Announce Type: cross Abstract: Self-supervised learning enables audio representations that transfer across domains and tasks.
By Ludovic K. Tuncay (IRIT-SAMoVA), Etienne Labb\'e (IRIT-SAMoVA), Thomas Pellegrini (IRIT-SAMoVA)