cs.SD · 2026-06-24 · No. 33

Sound, 2026-06-24.

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

01 — The papers

3 entries
  1. 01

    Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement

    Wangyi Pu, Michele Scarpiniti

    cs.SD · cs.AI · eess.AS

    Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment. Flow Matching offers an efficient alternative by transporting noisy speech toward clean speech through an ordinary differential equation with few function evaluations. In this work, we propose a skip-free encoder-decoder backbone for...

    arxiv.org/abs/2606.24745 · PDF

  2. 02

    ZONOS2 Technical Report

    Gabriel Clark, Sofian Mejjoute, Mohamed Osman, George Close, Beren Millidge

    cs.SD · cs.AI

    We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0.1 across scale, data, and training recipe. We scale the model from 1.6B to 8B total parameters (900M active) with a novel mixture-of-experts (MoE) backbone, improving inference latency and throughput. We expand our training corpus from 200K to over 6M hours using a new data processing pipeline,...

    arxiv.org/abs/2606.24320 · PDF

  3. 03

    Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation

    Baisen Wang, Chenxi Bao, Qisong Han

    cs.SD · cs.AI · cs.HC

    Interactive music and live performance relies on real-time human expression, but modern generative music AI remains largely absent from this domain due to its prohibitive inference latency and offline rendering paradigm. To provide pioneer musicians with a novel medium for interactive composition, we should fundamentally change these static models into dynamic, playable instruments. In this paper, we propose a framework that bridges this gap....

    arxiv.org/abs/2606.24307 · 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.