Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

Yujun Lin, Song Han, Huizi Mao, +2

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningData ScienceDistributed Algorithms +13

UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training

Hangbo Bao, Li Dong, Furu Wei, +8

arXiv (Cornell University)

Structured PredictionLlm Fine-tuningEngineeringMachine LearningMultilingual Pretraining +16

A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling

Yu Wang, Yilin Shen, Hongxia Jin

Natural Language ProcessingApplied LinguisticsSyntactic ParsingYilin ShenIntent Detection +12

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

Chaoqin Huang, Qinwei Xu, Yanfeng Wang, +2

IEEE Transactions on Multimedia

Anomaly DetectionMachine LearningEngineeringLocalizationUnsupervised Machine Learning +14

ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA

Song Han, Junlong Kang, Huizi Mao, +9

arXiv (Cornell University)

EngineeringMachine LearningAdvanced ComputingComputer ArchitectureShort-term Memory +19

Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Yu Wang, Xinsheng Wang, Pengcheng Zhu, +6

Interspeech 2022

MusicPopular Mandarin SongsEngineeringSpeech RecognitionNatural Language Processing +18

A data-driven non-intrusive measure of speech quality and intelligibility

Dushyant Sharma, Yu Wang, Patrick A. Naylor, +1

Speech Communication

Speech AnalysisHealth SciencesSpeech IntelligibilitySpeech ProcessingSpeech Quality +6

Towards automatic assessment of spontaneous spoken English

Yu Wang, Mark Gales, K.M. Knill, +4

Speech Communication

Natural Language ProcessingEngineeringComputational LinguisticsLanguage TestingLinguistics +7

Detection-based ASR in the automatic speech attribute transcription project

Ilana Bromberg, Qian Qian, Jun Hou, +8

EngineeringMachine LearningDetector DesignSpoken Language ProcessingSpeech Recognition +15

ESE: Efficient Speech Recognition Engine with Compressed LSTM on FPGA

Song Han, Junlong Kang, Huizi Mao, +9

arXiv (Cornell University)

EngineeringMachine LearningAdvanced ComputingComputer ArchitectureShort-term Memory +17