Rafael Valle
13 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (6) π Renaissance Researcher (5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
π
Century Club
(12)
β‘
Prolific Year
(6)
Conferences
ICLR (4)
ICML (4)
ACL (1)
EMNLP (1)
ICCV (1)
INTERSPEECH (1)
NIPS (1)
Top co-authors
Keywords
multilingual speech
(2)
preference alignment
(1)
speech synthesis
(1)
speech recognition
(1)
portrait animation
(1)
flow matching
(1)
speaker embedding
(1)
autoregressive model
(1)
classifier-free guidance
(1)
text-to-speech synthesis
(1)
speaker identity
(1)
voice preservation
(1)
facial expression
(1)
speaker adaptation
(1)
speech generation
(1)
head pose
(1)
facial landmark
(1)
speaker similarity
(1)
multilingual speech synthesis
(1)
large language model
(1)
Papers
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception
ACL 2026
Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance
EMNLP 2025
Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data
ICLR 2025
Fugatto 1: Foundational Generative Audio Transformer Opus 1
ICLR 2025
UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation
ICLR 2025
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
ICML 2025
ETTA: Elucidating the Design Space of Text-to-Audio Models
ICML 2025
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
ICML 2024
SelfVC: Voice Conversion With Iterative Refinement using Self Transformations
ICML 2024
RAD-MMM: Multilingual Multiaccented Multispeaker Text To Speech
INTERSPEECH 2023
SPACE: Speech-driven Portrait Animation with Controllable Expression
ICCV 2023
P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting
NIPS 2023
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
ICLR 2021