collaborators

7 papers

eess.AS2026

Too Good to Be True: A Study on Modern Automatic Speech Recognition for the Evaluation of Speech Enhancement

Danilo de Oliveira, Tal Peer, Timo Gerkmann

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is…

eess.AS2026

Do We Need EMA for Diffusion-Based Speech Enhancement? Toward a Magnitude-Preserving Network Architecture

Julius Richter, Danilo de Oliveira, Timo Gerkmann

We study diffusion-based speech enhancement using a Schrodinger bridge formulation and extend the EDM2 framework to this setting. We employ time-dependent preconditioning of networ…

eess.AS2025

Are These Even Words? Quantifying the Gibberishness of Generative Speech Models

Danilo de Oliveira, Tal Peer, Jonas Rochdi +1

Significant research efforts are currently being dedicated to non-intrusive quality and intelligibility assessment, especially given how it enables curation of large scale datasets…

eess.AS2025

LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models

Julius Richter, Danilo de Oliveira, Tal Peer +1

We present LipDiffuser, a conditional diffusion model for lip-to-speech generation synthesizing natural and intelligible speech directly from silent video recordings. Our approach…

eess.AS2025

Enhancing In-the-Wild Speech Emotion Conversion with Resynthesis-based Duration Modeling

Navin Raj Prabhu, Danilo de Oliveira, Nale Lehmann-Willenbrock +1

Speech Emotion Conversion aims to modify the emotion expressed in input speech while preserving lexical content and speaker identity. Recently, generative modeling approaches have…

eess.AS2025

Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech

Danilo de Oliveira, Julius Richter, Jean-Marie Lemercier +2

Diffusion models have found great success in generating high quality, natural samples of speech, but their potential for density estimation for speech has so far remained largely u…