Jordi Pons

4 papers · 2019–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ❓ The Questioner

Venues

Interspeech (2) ICLR (1) ICML (1)

Top co-authors

Zach Evans (2) CJ Carr (2) Anton Smirnov (1) Scott H. Hawley (1) Xubo Liu (1) Francesc Lluís (1) Julian D Parker (1) Nicolas Schmidt (1) Josiah Taylor (1) Xavier Serra (1)

Research topics

Deep Learning (4) Machine Learning (3) Architectures (3) Application Areas (2) Learning Types · Machine Learning (2) Models (2) Artificial Intelligence (1) Speech & Audio (1) Core AI (1) Learning Types · Deep Learning (1) Synthesis (1)

Keywords

transformer architecture (1) speech separation (1) source separation (1) deep learning (1) variational autoencoder (1) text prompt (1) latent diffusion (1) phase estimation (1) end-to-end model (1) speech coding (1) speech quality (1) neural audio codec (1) music source separation (1) low bitrate (1) waveform domain (1) music separation (1) podcast audio (1) generalization issue (1) finite scalar quantization (1) a100 gpu (1)

Papers

Scaling Transformers for Low-Bitrate High-Quality Speech Coding ICLR 2025 Fast Timing-Conditioned Latent Audio Diffusion ICML 2024 PodcastMix: A dataset for separating music and speech in podcasts Interspeech 2022 End-to-End Music Source Separation: Is it Possible in the Waveform Domain? Interspeech 2019