cs.SD · 2026-11-11 · No. 170

Sound, 2026-11-11.

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

    Exploring Post-Hoc Disentanglement of Audio Foundation Models for Music Similarity

    Lucas de Souza Brandão, Gabriel da Costa Merlin, Diego Furtado Silva

    cs.SD · cs.LG

    Audio foundation models like CLAP, MuQ, and MERT excel at capturing general musical similarity. On the other hand, their entangled latent spaces limit interpretability and fine-grained attribute control. Conditional Similarity Networks (CSN) address this by pairing a backbone representation model with learned masks that gate the embedding space into attribute-specific subspaces. However, existing methods train the backbone from scratch,...

    arxiv.org/abs/2611.14415 · PDF

  2. 02

    MusicFlux: Flexible Conditioning for Text-Guided Music Generation and Editing

    Teysir Baoueb, Leonardo Boulitreau de Menezes Martins Marques, Paraskevas Stamatiadis, Ga{ë}l Richard

    cs.SD · cs.AI · cs.LG · eess.SP

    Music editing transforms existing recordings while preserving their original attributes. Recent approaches adapt pretrained text-to-music models for tasks like inpainting, event insertion, or restoration by conditioning them with context audio. It was recently proposed for image editing to unify generation and editing by treating the source image as in-context information. However, applying this directly to music is computationally expensive...

    arxiv.org/abs/2611.13834 · PDF

  3. 03

    Swanada: Split-Encoder Capability-Routed Conformer CTC and Sub-30 MB On-Device Speech Recognition Across Twelve Scripts

    Hemanth HM

    cs.SD · cs.AI

    Client-side automatic speech recognition (ASR) across Indic and Classical scripts eliminates cloud transcription costs, network tail latency, and server-side audio retention, yet neural exports face four systems bottlenecks in browsers and mobile runtimes: (1) monolithic per-language Conformer checkpoints require ~177 MiB per script (> 2.1 GiB across 12 scripts), exhausting CacheStorage quotas; (2) static relative positional encoding tables...

    arxiv.org/abs/2611.13814 · PDF

  4. 04

    AURA: Auditory Spatial Intelligence via a Unified Representation from a General-Audio Encoder through Complete Alignment

    Boyan Han, Xiaoyan Wang, Zhe Sun, Ziqi Wang, Yujun Cai, Hongli Cao, Yiwei Wang, Ming-Hsuan Yang, Liang An

    cs.SD · cs.AI

    Answering spatial questions about multi-source scenes requires a model both to identify each sound and to locate it. Existing spatial audio-language models obtain spatial information from a dedicated encoder, which separates spatial and semantic processing into distinct feature spaces. We study whether a general-audio codec trained without spatial supervision can serve both purposes. A controlled layer-wise analysis shows that the frozen...

    arxiv.org/abs/2611.13687 · 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.