Tal Remez
12 papers · 2017–2024 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (14)
π
Conference Polyglot
(7)
π
Academic Marathon
(7)
π
Cross-Pollinator
(5)
π
Century Club
(12)
π
Conference Pioneer
Conferences
NIPS (3)
CVPR (2)
ECCV (2)
ICLR (2)
ICCV (1)
ICML (1)
INTERSPEECH (1)
Top co-authors
Keywords
speech synthesis
(2)
multimodal learning
(2)
code generation
(1)
conditional generation
(1)
flow matching
(1)
language model
(1)
discrete diffusion
(1)
audio-visual speech
(1)
language generation
(1)
speech-to-speech translation
(1)
end-to-end translation
(1)
voice preservation
(1)
probability path
(1)
music generation
(1)
speech language model
(1)
expressive speech synthesis
(1)
discrete expressive speech resynthesis
(1)
self-supervised discrete encoder
(1)
textless speech synthesis
(1)
non-autoregressive generation
(1)
Papers
Masked Audio Generation using a Single Non-Autoregressive Transformer
ICLR 2024
Discrete Flow Matching
NIPS 2024
ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration
CVPR 2023
Simple and Controllable Music Generation
NIPS 2023
Textually Pretrained Speech Language Models
NIPS 2023
Expresso: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
INTERSPEECH 2023
AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation
ECCV 2022
More Than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech
CVPR 2022
Translatotron 2: High-quality direct speech-to-speech translation with voice preservation
ICML 2022
Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
ICLR 2021
Learning to Segment via Cut-and-Paste
ECCV 2018
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
ICCV 2017