cs.SD · 2026-06-18 · No. 27

Sound, 2026-06-18.

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

    Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

    Michael Finkelson, Daniel Segal, Eitan Richardson, Shahar Armon, Nani Goldring, Poriya Panet, Nir Zabari, Benjamin...

    cs.SD · cs.AI · cs.CV

    Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations. We take a different approach. Our method, ScenA, conditions a text-to-audio flow-matching foundation model, pretrained on...

    arxiv.org/abs/2606.19325 · PDF

  2. 02

    Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation

    Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas, Theodoros Giannakopoulos, Themos Stafylakis

    cs.SD · cs.AI · cs.LG

    Transformer-based architectures have significantly advanced the generation of complex symbolic sequences, yet a significant gap remains in achieving fine-grained, interpretable control over discrete signal attributes. This paper investigates the mechanistic interpretability of the Multitrack Music Transformer (MMT) and proposes a framework for deterministic attribute modulation without retraining to bridge this gap via inference-time...

    arxiv.org/abs/2606.18790 · PDF

  3. 03

    NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization

    Yizhuo Yang, Junqiao Fan, Shenghai Yuan, Lihua Xie

    cs.SD · cs.AI

    Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments. Classical methods such as Multiple Signal Classification (MUSIC) offer strong theoretical foundations but degrade under low signal-to-noise ratios. While deep learning-based approaches achieve promising performance, they often struggle with limited generalization across...

    arxiv.org/abs/2606.18664 · PDF

  4. 04

    QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement

    Shogo Yamauchi, Hideaki Tamori, Makoto Sakai, Yosuke Yamano, Tohru Nitta

    cs.SD · cs.AI · cs.LG · stat.ML

    We propose a parameter-efficient speech enhancement framework, Quaternion Conformer GAN (QC-GAN), which combines a Quaternion Conformer generator with MetricGAN-based training. The Hamilton product encodes the magnitude and phase via structured weight sharing, reducing the number of layer parameters while preserving their interdependencies. A metric-learning discriminator was employed to maximize perceptual quality by optimizing the...

    arxiv.org/abs/2606.18611 · 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.