AIConfPaper
← Search

Emilian Postolache

8 accepted papers

2025

COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations

Ruben Ciranni, Giorgio Mariani, Michele Mancusi, Emilian Postolache, Giorgio Fabbro, Emanuele Rodolà +1
ICASSP 2025accepted

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of the individual stems composing music tracks and can input feat…

Cited by 0Source ↗Scholar ↗
2025

Naturalistic Music Decoding from EEG Data via Latent Diffusion Models

Emilian Postolache, Natalia Polouliakh, Hiroaki Kitano, Akima Connelly, Emanuele Rodolà, Luca Cosmo +1
ICASSP 2025accepted

In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroencephalogram (EEG) recordings. Unlike simpler music with limited timbres, such as MIDI-generated tunes or monophonic piec…

Cited by 0Source ↗Scholar ↗
2024

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

Emilian Postolache, Giorgio Mariani, Luca Cosmo, Emmanouil Benetos, Emanuele Rodolà
ICASSP 2024accepted

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the joint distribution over the sources, necessitating pre-separa…

Cited by 0Source ↗Scholar ↗
2024

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

Giorgio Mariani, Irene Tallini, Emilian Postolache, Michele Mancusi, Luca Cosmo, Emanuele Rodolà
ICLR 2024oral

In this work, we define a diffusion-based generative model capable of both music generation and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference tasks (i.e., generating a mixture, separating the sources), we…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗
2024

Syncfusion: Multimodal Onset-Synchronized Video-to-Audio Foley Synthesis

Marco Comunità, Riccardo F. Gramaccioni, Emilian Postolache, Emanuele Rodolà, Danilo Comminiello, Joshua D. Reiss
ICASSP 2024accepted

Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality. One of the most time-consuming steps when designing sound is synchronizing audio with video. In some cases, environmental recordings from video…

Cited by 0Source ↗Scholar ↗
2023

Accelerating Transformer Inference for Translation via Parallel Decoding

Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin +1
ACL 2023long

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model, trading inference speed at the cost of the transl…

Cited by 82Source ↗PDF ↗code ↗Scholar ↗
2023

Adversarial Permutation Invariant Training for Universal Sound Separation

Emilian Postolache, Jordi Pons, Santiago Pascual, Joan Serrà
ICASSP 2023accepted

Universal sound separation consists of separating mixes with arbitrary sounds of different types, and permutation invariant training (PIT) is used to train source agnostic models that do so. In this work, we complement PIT with adversarial losses but find it challenging with the standard formulation…

Cited by 0Source ↗Scholar ↗
2023

Latent Autoregressive Source Separation

Emilian Postolache, Giorgio Mariani, Michele Mancusi, Andrea Santilli, Luca Cosmo, Emanuele Rodolà
AAAI 2023technical

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.g., obtained via VQ-VAE autoencoders), which allow…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗