cs.SD · 2026-07-30 · No. 69

Sound, 2026-07-30.

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

01 — The papers

4 entries
  1. 01

    MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning

    Weijie Wu, Junbo Li, Lin Li, Jun Fang, Qingyang Hong

    cs.SD · cs.AI

    With the development of audio large language models (AudioLLMs), audio captioning needs to move from brief descriptions toward open-ended and fine-grained free-form descriptions. Existing evaluations often focus on generation quality or task performance, making it difficult to diagnose information coverage and description reliability. We propose MMAC, a \textbf{M}assive \textbf{M}ulti-dimensional benchmark for \textbf{A}udio...

    arxiv.org/abs/2607.27109 · PDF

  2. 02

    MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation

    Wei-Jaw Lee, Hsuan-Yu Yeh, Ting-Yi Hu, Chih-Pin Tan, Fang-Duo Tsai, Yi-Hsuan Yang

    cs.SD · cs.AI · eess.AS

    Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we...

    arxiv.org/abs/2607.26698 · PDF

  3. 03

    Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement

    Tianyan Deng, Yanxiong Li, Rui Gao, Jiahao Du

    cs.SD · cs.LG

    Few-shot Open-set audio classification requires classifying query samples from known classes with a few labeled support samples while rejecting query samples from unknown classes. Transductive inference jointly observes the full unlabeled query set to improve prototype estimation, yet standard transductive updates do not distinguish known from unknown query samples, leaving prototypes vulnerable to open-set contamination. Drawing on...

    arxiv.org/abs/2607.26607 · PDF

  4. 04

    Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection

    Haotian Mo, Jie Liu, Siqi Shen, Songzhu Mei, Xinhai Chen, Xiangyang Wang, Yigui Feng, Shuai Li, Gencheng Liu, Keqi...

    cs.SD · cs.AI

    Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on bona fide speech, as a frozen reconstruction probe. Reconstructions at masking ratios 0.5, 0.75, and 0.9 yield explicit multi-ratio residual maps. Because these residuals are domain sensitive, our audio-anchored detector passes the projected frozen-WavLM auditory representation into the fusion...

    arxiv.org/abs/2607.26472 · PDF

This edition is part of The Daily Abstract — cs.SD 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.