cs.SD · 2026-06-16 · No. 25

Sound, 2026-06-16.

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

01 — The papers

7 entries
  1. 01

    TuneJury: An Open Metric for Improving Music Generation Preference Alignment

    Yonghyun Kim, Junwon Lee, Haiwen Xia, Yinghao Ma, Junghyun Koo, Koichi Saito, Yuki Mitsufuji, Chris Donahue

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

    We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released checkpoint is trained on publicly available human-preference labels covering arena-style (A vs. B) votes, metric-alignment preference pairs, crowdsourced pairwise comparisons, and expert aesthetic ratings. The predicted score margin between two clips is well calibrated...

    arxiv.org/abs/2606.17006 · PDF

  2. 02

    Probing Low Frame Rate Degradation in Neural Audio Codecs

    Alex Gichamba, Moise Busogi

    cs.SD · cs.AI · eess.AS

    Low frame rates in neural audio codecs are attractive for autoregressive speech synthesis, where the generation cost scales linearly with the sequence length. Recent work has demonstrated that codecs can operate at 12.5 Hz and below, but the mechanisms underlying low frame rate degradation remain insufficiently understood. We investigate these mechanisms through a controlled frame rate ablation. We reproduce a quality cliff at 6.25 Hz...

    arxiv.org/abs/2606.16969 · PDF

  3. 03

    MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild

    Haotian Qi, Gabriel Skantze

    cs.SD · cs.AI · cs.HC

    Current multiparty turn-taking models often rely on complex microphone arrays or multi-camera setups, limiting their applicability in human-robot interaction scenarios. We introduce MuVAP, a causal multimodal framework that extends Voice Activity Projection by grounding acoustic predictions in face tracks, enabling speaker-aware turn-taking predictions from a monaural audio stream and a single camera view. To address the combinatorial...

    arxiv.org/abs/2606.16731 · PDF

  4. 04

    Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

    Yan Han, Zhibin Wen, Yuan Wang, Shuangrun Shao, Xiaobing Li, Yang Xu, Wei Li

    cs.SD · cs.LG · cs.MM

    The rapid advancement of AI music generators highlights the urgent need for reliable Synthetic Song Detection (SSD). Existing SSD methods often rely on low-level artifacts or fixed feature assumptions, struggling to capture generator-agnostic cues. To address this, we propose Sofia (Synthetic-song detection framework via music features), a flexible framework that models music-intrinsic attributes via feature-specific experts and an adaptive...

    arxiv.org/abs/2606.16612 · PDF

  5. 05

    ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition

    Zeqian Hu, Fuliang Weng, Shu Shang, Yaqian Zhou

    cs.SD · cs.AI

    Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations. Echoing joint-embedding predictive architecture (JEPA) work in vision, we propose ArtNet, a framework that explores a structured feature prediction task based on articulatory features to enhance acoustic robustness. Specifically, ArtNet integrates an articulatory predictor,...

    arxiv.org/abs/2606.16595 · PDF

  6. 06

    Dual-Granularity Orthogonal Disentanglement for Generalizable Audio Deepfake Detection

    Zhuodong Liu, Hugen Lv, Xiangyu Li, Chunhong Yuan

    cs.SD · cs.AI

    Audio deepfake detectors often fail to generalize across speakers, as they learn speaker-identity features rather than synthesis artifacts, known as implicit identity leakage. Existing methods address this but incur architectural complexity or training instability. This paper proposes a dual-granularity orthogonal disentanglement framework enforcing feature independence at two levels: sample-level cosine orthogonality captures directional...

    arxiv.org/abs/2606.16532 · PDF

  7. 07

    Semi-Supervised Speech Confidence Detection using Pseudo-Labelling and Whisper Embeddings

    Adam Wynn, Jingyun Wang, Xiangyu Tan

    cs.SD · cs.LG

    Understanding speaker confidence is crucial in educational settings, as it can enhance personalised feedback and improve learning outcomes. This study introduces a novel framework for detecting speaker confidence by integrating human-engineered features with embeddings from the Whisper encoder. To address data limitations, a pseudo-labelling technique is employed to expand the labelled dataset, allowing the model to learn from both...

    arxiv.org/abs/2606.16505 · 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.