RESEARCH
NLP
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
April 16, 2020
Abstract
We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables the direct application of algorithms from the NLP community which require discrete inputs. Experiments show that BERT pre-training achieves a new state of the art on TIMIT phoneme classification and WSJ speech recognition.
AUTHORS
Publisher
ICLR
Research Topics
Related Publications
March 13, 2025
NLP
COMPUTER VISION
Subobject-level Image Tokenization
Delong Chen, Samuel Cahyawijaya, Jianfeng Liu, Baoyuan Wang, Pascale Fung
March 13, 2025
February 27, 2025
INTEGRITY
THEORY
Logic.py: Bridging the Gap between LLMs and Constraint Solvers
Pascal Kesseli, Peter O'Hearn, Ricardo Silveira Cabral
February 27, 2025
February 07, 2025
NLP
BOUQuET: dataset, Benchmark and Open initiative for Universal Quality Evaluation in Translation
The Omnilingual MT Team, Pierre Andrews, Mikel Artetxe, Mariano Coria Meglioli, Marta R. Costa-jussa, Joe Chuang, David Dale, Cynthia Gao, Jean Maillard, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Eduardo Sánchez, Yiannis Tsiamas, Arina Turkatenko, Albert Ventayol, Shireen Yates
February 07, 2025
February 07, 2025
RESEARCH
SPEECH & AUDIO
Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
Andros Tjandra, Yi-Chiao Wu, Baishan Guo, John Hoffman, Brian Ellis, Apoorv Vyas, Bowen Shi, Sanyuan Chen, Matt Le, Nick Zacharov, Carleigh Wood, Ann Lee, Wei-Ning Hsu
February 07, 2025
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Foundational models
Our approach
Latest news
Foundational models
Meta © 2025