SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Daniel Park, William Chan, Yu Zhang, +4

Image Super-Resolution Via Iterative Refinement

Chitwan Saharia, Jonathan Ho, William Chan, +3

IEEE Transactions on Pattern Analysis and Machine Intelligence

EngineeringMachine LearningSuper-resolution ImagingImage AnalysisData Science +14

Palette: Image-to-Image Diffusion Models

Chitwan Saharia, William Chan, Huiwen Chang, +5

EngineeringMachine LearningMultimodal LlmImage AnalysisData Science +16

Cascaded Diffusion Models for High Fidelity Image Generation

Jonathan Ho, Chitwan Saharia, William Chan, +3

arXiv (Cornell University)

EngineeringMachine LearningCascaded Diffusion ModelImage AnalysisData Science +15

Listen, Attend and Spell

William Chan, Navdeep Jaitly, Quoc V. Le, +1

arXiv (Cornell University)

EngineeringSpeech CorpusSpeech UtterancesNeural NetworkSpoken Language Processing +15

Insertion Transformer: Flexible Sequence Generation via Insertion Operations

Mitchell Stern, William Chan, Jamie Kiros, +1

arXiv (Cornell University)

EngineeringMachine LearningInsertion TransformerMultilingual PretrainingSequence Design +17

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

Yu Zhang, Daniel Park, Wei Han, +23

IEEE Journal of Selected Topics in Signal Processing

Specaugment on Large Scale Datasets

Daniel Park, Yu Zhang, Chung‐Cheng Chiu, +5

EngineeringMachine LearningLarge-scale DatasetsAdaptive MaskingSpeech Recognition +20

Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes

Bo Li, Yu Zhang, Tara N. Sainath, +2

EngineeringLarge Language ModelCorpus LinguisticsSpeech RecognitionNatural Language Processing +19

SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network

William Chan, Daniel Park, Chris A. Lee, +3

arXiv (Cornell University)

EngineeringMachine LearningSpoken Language ProcessingMultilingual PretrainingExternal Language Model +16