Showing 1–20 of 74 results
/ Date/ Name
Feb 7, 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageOct 12, 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech RepresentationsJul 15, 2019GLOSS: Generative Latent Optimization of Sentence RepresentationsOct 18, 2022Simple and Effective Unsupervised Speech TranslationFeb 10, 2023AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target RepresentationsJul 25, 2024Scaling A Simple Approach to Zero-Shot Speech RecognitionSep 27, 2024Improving Multilingual ASR in the Wild Using Simple N-best Re-rankingOct 20, 2016Iterative Refinement for Machine TranslationNov 12, 2025Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ LanguagesApr 25, 2022On-demand compute reduction with stochastic wav2vec 2.0Nov 28, 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingAug 15, 2019Simple and Effective Noisy Channel Modeling for Neural Machine TranslationJul 22, 2019ELI5: Long Form Question AnsweringFeb 20, 2019Mixture Models for Diverse Machine Translation: Tricks of the TradeJun 30, 2016Neural Network-based Word Alignment through Score AggregationDec 14, 2022Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and LanguageJun 27, 2022Wav2Vec-Aug: Improved self-supervised training with limited dataNov 13, 2020Language Models not just for Pre-training: Fast Online Neural Noisy Channel ModelingApr 11, 2019wav2vec: Unsupervised Pre-training for Speech RecognitionAug 28, 2018Understanding Back-Translation at Scale