Marco Pasini

19 papers Misc 2Journal 13Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Diffusion Timbre Transfer Via Mutual Information Guided Inpainting.
CoRR
Ching Ho Lee, Javier Nistal, Stefan Lattner, Marco Pasini, George Fazekas
2025 — conf
CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio.
ISMIR
Marco Pasini, Stefan Lattner, George Fazekas
2025 J jnl
CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2025 Misc conf
Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding.
ICASSP
Marco Pasini, Stefan Lattner, György Fazekas
2025 J jnl
Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2025 J jnl
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders.
CoRR
Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini, Stefan Lattner, Gerhard Widmer
2025 J jnl
Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation.
CoRR
Aditya Bhattacharjee, Marco Pasini, Emmanouil Benetos
2024 Misc conf
Bass Accompaniment Generation Via Latent Diffusion.
ICASSP
Marco Pasini, Maarten Grachten, Stefan Lattner
2024 J jnl
Bass Accompaniment Generation via Latent Diffusion.
CoRR
Marco Pasini, Maarten Grachten, Stefan Lattner
2024 J jnl
Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation.
CoRR
Marco Pasini, Javier Nistal, Stefan Lattner, George Fazekas
2024 J jnl
Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models.
CoRR
Javier Nistal, Marco Pasini, Cyran Aouameur, Maarten Grachten, Stefan Lattner
2024 — conf
Diff-a-Riff: Musical Accompaniment Co-Creation via Latent Diffusion Models.
ISMIR
Javier Nistal, Marco Pasini, Cyran Aouameur, Maarten Grachten, Stefan Lattner
2024 J jnl
Improving Musical Accompaniment Co-creation via Diffusion Transformers.
CoRR
Javier Nistal, Marco Pasini, Stefan Lattner
2024 — conf
Music2Latent: Consistency Autoencoders for Latent Audio Compression.
ISMIR
Marco Pasini, Stefan Lattner, George Fazekas
2024 J jnl
Music2Latent: Consistency Autoencoders for Latent Audio Compression.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2023 J jnl
Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2022 — conf
Musika! Fast Infinite Waveform Music Generation.
ISMIR
Marco Pasini, Jan Schlüter
2022 J jnl
Musika! Fast Infinite Waveform Music Generation.
CoRR
Marco Pasini, Jan Schlüter
2019 J jnl
MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms.
CoRR
Marco Pasini