Showing 1–20 of 56 results
/ Date/ Name
Feb 20, 2020Imputer: Sequence Modelling via Imputation and Dynamic ProgrammingApr 7, 2021Pushing the Limits of Non-Autoregressive Speech RecognitionApr 18, 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech RecognitionJun 4, 2019KERMIT: Generative Insertion-Based Modeling for SequencesAug 1, 2019Bounds on Continuous Scott RankNov 12, 2017Ordinal Definability and Combinatorics of Equivalence RelationsMay 23, 2022Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingApr 7, 2015Deep Recurrent Neural Networks for Acoustic ModellingJan 28, 2016The Countable Admissible Ordinal Equivalence RelationOct 10, 2016Latent Sequence DecompositionsApr 16, 2020Non-Autoregressive Machine Translation with Latent AlignmentsMay 30, 2021Cascaded Diffusion Models for High Fidelity Image GenerationSep 27, 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech RecognitionSep 13, 2017Definable Combinatorics of Some Borel Equivalence RelationsDec 3, 2017Scott Ranks of Classifications of the Admissibility Equivalence RelationNov 22, 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with BytesOct 5, 2022Imagen Video: High Definition Video Generation with Diffusion ModelsNov 10, 2021Palette: Image-to-Image Diffusion ModelsJun 7, 2021Learning to Efficiently Sample from Diffusion Probabilistic ModelsAug 17, 2016When an Equivalence Relation with All Borel Classes will be Borel Somewhere?