eess.AS · 2026-09-23 · No. 122
Audio and Speech Processing, 2026-09-23.
2 new papers in eess.AS. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Not Quite My Tempo: Voice Activity-aware Speech Synthesis for Lip-Synchronous Dubbing
Alejandro Pérez-González-de-Martos, Florian Lux, Angelina Elizarova, Milana Shkhanukova, Andreas Kellner, Mattia...
eess.AS · cs.AI
Automatic lip-synchronous dubbing requires a speech synthesis model to generate alternating voice and silence patterns in the target language that match the timing of the source clip precisely to ensure an optimal viewing experience. Prior works address this problem by conditioning the speech synthesis process on lip movements extracted from the video signal. In this work, we condition the speech generation on a binary voice-activity signal,...
-
02
SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schrödinger Bridges
Andreas Bagge, Andreas Nymand, Michael Riis Andersen, Bjørn Sand Jensen
eess.AS · cs.AI · cs.SD
Speech enhancement (SE) models typically rely on supervised learning with paired data examples where clean speech is synthetically degraded. This paradigm limits performance in real-world scenarios where the target environment's specific acoustic characteristics are unknown. We propose a fully unpaired SE framework that uses principled Diffusion Schrödinger Bridges (DSB) to learn a stochastic transport process between a clean and a degraded...
This edition is part of The Daily Abstract — eess.AS 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.