cs.SD · 2026-11-10 · No. 169

Sound, 2026-11-10.

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

    WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

    Sang-Hoon Lee, Ha-Yeong Choi

    cs.SD · cs.AI · eess.AS · eess.SP

    This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral trajectory and the target waveform trajectory within a single model, enabling direct end-to-end text-to-waveform generation. Unlike recent TTS pipelines, WaveGen does not rely on separately trained or externally decoded intermediate representations, such as neural audio codecs,...

    arxiv.org/abs/2611.12527 · PDF

  2. 02

    AudioCodex: Streaming Autoencoders for Live Audio

    Marco Pasini, Javier Nistal, Cyran Aouameur, Stefan Lattner, George Fazekas

    cs.SD · cs.LG · eess.AS

    We introduce AudioCodex, a fully causal autoencoder for live generative audio applications that compresses stereo audio into compact continuous latent sequences at ~10 Hz. It combines a Mean Flow magnitude autoencoder with latent hypersphere projection, bounded-noise augmentation, representation alignment, and adversarial phase recovery to learn representations that support both efficient downstream generation and high-quality reconstruction....

    arxiv.org/abs/2611.12375 · PDF

  3. 03

    BARS: Beat-Adaptive Rap Synthesis via Flow Matching

    Taemin Cho, Hector Martel, Enyan Koh

    cs.SD · cs.LG · cs.MM · eess.AS

    We present BARS (Beat-Adaptive Rap Synthesis), a non-autoregressive rapping voice generation model based on Flow Matching, conditioned on a beat track (instrumental backing), lyrics, and a short reference voice for zero-shot timbre control. Unlike prior autoregressive rap synthesis, where rap pace and output duration are strictly determined by the beat, BARS enables independent control over the rap tempo, allowing flexible-length generation...

    arxiv.org/abs/2611.12061 · PDF

  4. 04

    MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection

    Donghyun Kim, Jin Hong, Seungmin Kim, Dain Kim, Junseok Kwon, Daeseon Choi

    cs.SD · cs.CV · cs.LG

    Talking-head generation models, which synthesize realistic facial animations from audio, are increasingly vulnerable to misuse in multimodal deepfake scenarios. Protecting such systems remains challenging, as talking-head models fundamentally rely on precise audio-visual alignment, while effective audio protection methods remain largely underexplored. In this work, we propose MUTE, an audio protection framework that uncouples the underlying...

    arxiv.org/abs/2611.11989 · 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.