Search

GLADIA
GLADIA
  • Home
  • News
  • Publications
  • People
  • NeXuS
  • Blog
  • Contact
Emilian Postolache

Emilian Postolache

Lead Machine Learning Researcher, IRIS Audio

IRIS Audio Technologies

Lead Machine Learning Researcher @ Iris Audio Technologies. Previous: Sapienza University of Rome (PhD), Ca’ Foscari University of Venice (PostDoc), Queen Mary University of London (Visitor), Dolby Labs (Intern) and Sony CSL Tokyo (Intern).

Interests
  • Tiny ML
  • Speech Enhancement
  • Audio Super Resolution
  • Sequence models
  • Generative models
  • Signal processing
  • Source separation

Latest

  • COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
  • Naturalistic Music Decoding from EEG Data via Latent Diffusion Models
  • Papers accepted at ICASSP 2025
  • Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
  • SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis
  • Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models
  • Papers accepted at ICASSP 2024
  • Paper accepted as Oral at ICLR 2024
  • Zero-Shot Duet Singing Voices Separation with Diffusion Models
  • Adversarial Permutation Invariant Training for Universal Sound Separation
  • Accelerating Transformer Inference for Translation via Parallel Decoding
  • Latent Autoregressive Source Separation
  • Unsupervised source separation via Bayesian inference in the latent domain
  • A parametric analysis of discrete Hamiltonian functional maps

Emanuele Rodolà © 2026 – Made by Donato Crisostomi, maintained by Donato Crisostomi, Andrea Santilli and Luca Moschella.

Published with Wowchemy — the free, open source website builder that empowers creators.

Cite
Copy Download