cs.SD · 2026-06-06 · No. 15

Sound, 2026-06-06.

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

01 — The papers

2 entries
  1. 01

    F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

    Dinghao Zhou, Xingchen Song, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang Lv

    cs.SD · cs.AI · eess.AS

    Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and generation. We adapt continuous autoencoder latents to this setting with two components: a noise-regularized autoencoder bottleneck and a...

    arxiv.org/abs/2606.06357 · PDF

  2. 02

    DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement

    Cunhang Fan, Enrui Liu, Jing Zhou, Jian Kang, Jie Li, Andong Li, Jian Zhou, Zhao Lv, Xuelong Li

    cs.SD · cs.LG · eess.AS

    Although artificial neural network (ANN) based speech enhancement (SE) methods demonstrate excellent performance, the high computational complexity and high energy consumption hinder their deployment in practical front-end processing tasks.} Currently, the spiking neural networks (SNNs) have shown potential in reducing power consumption. However, the discrete binary activation and complex spatio-temporal dynamics of SNNs often result in...

    arxiv.org/abs/2606.05911 · 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.