Joan Serrร
8 papers · 2017–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
๐ Cross-Pollinator (15) ๐ Academic Marathon (8) ๐ Renaissance Researcher (5) ๐ Interdisciplinary Bridge ๐ฃ Hot Topic Early Bird
๐
Conference Polyglot
(5)
๐บ๏ธ
Taxonomy Completionist
(11)
๐งญ
Keyword Pioneer
๐
Keyword Champion
๐
Trend Setter
Conferences
INTERSPEECH (3)
ICML (2)
ECCV (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
speech enhancement
(2)
generative adversarial network
(2)
catastrophic forgetting
(1)
transfer learning
(1)
feature extraction
(1)
self-supervised learning
(1)
voice conversion
(1)
speech processing
(1)
signal reconstruction
(1)
sequential learning
(1)
normalizing flow
(1)
end-to-end training
(1)
speaker identity
(1)
hard attention
(1)
noise condition
(1)
raw audio
(1)
speaker conversion
(1)
time-domain processing
(1)
non-parallel training
(1)
neural network
(1)
Papers
Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching
ICML 2025
Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity
ECCV 2024
Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models
ICLR 2020
Towards Generalized Speech Enhancement with Generative Adversarial Networks
INTERSPEECH 2019
Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks
INTERSPEECH 2019
Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
NIPS 2019
Overcoming Catastrophic Forgetting with Hard Attention to the Task
ICML 2018
SEGAN: Speech Enhancement Generative Adversarial Network
INTERSPEECH 2017