eess.AS · 2026-07-16 · No. 55

Audio and Speech Processing, 2026-07-16.

4 new papers in eess.AS. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

4 entries
  1. 01

    Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification

    Shiqi Zhang, Tuomas Virtanen

    eess.AS · cs.AI · cs.SD

    Sound event detection relies on frame-level strong labels whose annotation is expensive. Active learning addresses this problem by selecting the audio segments whose labels help the classifier most. One of the prevailing acquisition strategies for this task, mismatch-first farthest-traversal (MFFT), combines the disagreement between two classifiers and the diversity of the selected segments through hard sequential decisions. It selects whole...

    arxiv.org/abs/2607.13571 · PDF

  2. 02

    Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning

    Shiqi Zhang, Marius Faiß, Ariana Strandburg-Peshkin, Tuomas Virtanen

    eess.AS · cs.AI · cs.SD

    Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert annotation and using the labeled segments for training the classifier. The setting is hard: the target calls are extremely sparse and the call-type distribution is long-tailed, so a tight budget must be spent on the few rare, informative segments. We propose BADGE-Greedy-DPP, a...

    arxiv.org/abs/2607.13555 · PDF

  3. 03

    Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models

    Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qinming Tang, Ankur Gandhe, Hung-yi Lee, Chieh-Chi...

    eess.AS · cs.AI · cs.CL · cs.LG · cs.SD

    Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing evaluation and training signals mainly emphasize global similarity or perceptual quality, with limited supervision on instruction-level correctness. We propose an instruction-level framework that uses audio-aware large language models (ALLMs) as fine-grained judges...

    arxiv.org/abs/2607.13408 · PDF

  4. 04

    Efficient Text-to-Audio Generation via Pruning

    Arshdeep Singh, Yi Yuan, Yun Chen, Wenwu Wang, Mark D. Plumbley

    eess.AS · cs.AI

    Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency; however, their practical deployment is hindered by the substantial computational cost of the U-Net denoising backbone. In this work, we apply model pruning to improve the computational efficiency of AudioLDM, a U-Net-based text-conditioned audio latent diffusion model. We analyse parameter redundancy across U-Net...

    arxiv.org/abs/2607.13330 · PDF

This edition is part of The Daily Abstract — eess.AS archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.