Michele Mancusi

According to our database, Michele Mancusi authored at least 6 papers between 2021 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation.

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

CoRR, 2023

Exploiting Music Source Separation For Singing Voice Detection.

Francesco Bonzi, Michele Mancusi, Simone Del Deo, Pierfrancesco Melucci, Maria Stella Tavella, Loreto Parisi, Emanuele Rodolà

Proceedings of the 33rd IEEE International Workshop on Machine Learning for Signal Processing, 2023

Accelerating Transformer Inference for Translation via Parallel Decoding.

Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, Emanuele Rodolà

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Latent Autoregressive Source Separation.

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

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Fish sounds: towards the evaluation of marine acoustic biodiversity through data-driven audio source separation.

Michele Mancusi, Nicola Zonca, Emanuele Rodolà, Silvia Zuffi

CoRR, 2022

2021

Unsupervised Source Separation via Bayesian Inference in the Latent Domain.

Michele Mancusi, Emilian Postolache, Marco Fumero, Andrea Santilli, Luca Cosmo, Emanuele Rodolà

CoRR, 2021