14 papers
DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling
Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis +3
Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this…
Scaling Beyond Masked Diffusion Language Models
Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang +4
Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion c…
Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens
Pin-Jui Ku, He Huang, Jean-Marie Lemercier +3
This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a dis…
HRTF Estimation using a Score-based Prior
Etienne Thuillier, Jean-Marie Lemercier, Eloi Moliner +2
We present a head-related transfer function (HRTF) estimation method which relies on a data-driven prior given by a score-based diffusion model. The HRTF is estimated in reverberan…
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…
Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models
Jean-Marie Lemercier, Eloi Moliner, Simon Welker +2
This paper presents an unsupervised method for single-channel blind dereverberation and room impulse response (RIR) estimation, called BUDDy. The algorithm is rooted in Bayesian po…