The paper introduces LAST, a Looped Audio Spectrogram Transformer that processes all tokens once and then reuses the same blocks to refine only the class token over fixed audio features, making subsequent passes inexpensive. On AudioSet, a ten‑pass LAST outperforms a twelve‑layer sequential transformer by 2.1% relative mean average precision while using 49.4% fewer parameters, 42% fewer MACs, and achieving 9.8% higher throughput. Increasing the pass count from two to ten improves accuracy with only a 1.2% increase in computation, and the model shows enhanced robustness to temporal masking and other auditory augmentations across music, environmental, and event sound classification tasks.
By Haider Al-Tahan, Sean O'Brien, Anastasia Razdaibiedina, N. Apurva Ratan Murty
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.
By Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne, Rogerio Feris, James Glass
AudioFuse is a hybrid architecture that jointly learns from spectrograms and raw waveforms to classify phonocardiograms. It combines a wide-and-shallow Vision Transformer for spectral features with a shallow 1D CNN for temporal waveforms, reducing overfitting while capturing complementary information. On the PhysioNet 2016 dataset, AudioFuse achieves a state‑of‑the‑art ROC‑AUC of 0.8608 and shows superior robustness to domain shift on the PASCAL dataset, outperforming both spectrogram‑only and waveform‑only baselines.
By Md. Saiful Bari Siddiqui, Utsab Saha
arXiv:2604. 01832v1 Announce Type: cross Abstract: We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge.
By Xiaobin Rong, Yushi Wang, Zheng Wang, Jing Lu
arXiv:2608.30927v1 Announce Type: cross
Abstract: Whisper exposes speech through a fixed 1500-token encoder interface, now a default representation for ASR decoders and Whisper-based speech language...
By Chanhee Cho, Junhyuk Choi, Bugeun Kim
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)
arXiv:2609.24138v1 Announce Type: cross
Abstract: Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has c...
By Ningyuan Yang, Yize Li, Pu Zhao, Diego A. Cuji, Kanad Sarkar, Ryan M. Corey, Xue Lin, Andrew C. Singer
Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has concentrated on standard or versatile SSR configurat...
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. 14791v1 Announce Type: cross Abstract: Self-supervised learning advances audio representation for multimedia analysis.
By Fengrui Liu, Ruiyang Huang, Qijian Zheng, Yuanfang Wang, Feng Liu
arXiv:2606. 06907v1 Announce Type: cross Abstract: Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data.
By Seonuk Kim, Yonghyeon Jun, Ju Yeon Kang, Jimin Hong, Yoonhyeong Lee, Nam Soo Kim
arXiv:2601. 09239v5 Announce Type: replace-cross Abstract: Speech tokenizers are a key building block of fully discrete Speech LLMs.
By Hanlin Zhang, Daxin Tan, Dehua Tao, Xiao Chen, Haochen Tan, Yunhe Li, Yuchen Cao, Linqi Song