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-
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,...
-
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....
-
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...
-
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...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.