Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks

Daniel Povey, Gaofeng Cheng, Yiming Wang, +4

Deep Neural NetworksEngineeringMachine LearningMatrix FactorizationSparse Neural Network +2

Transformer-Based Online CTC/Attention End-To-End Speech Recognition Architecture

Haoran Miao, Gaofeng Cheng, Changfeng Gao, +2

EngineeringMachine LearningOnline RecognitionSpoken Language ProcessingSpeech Recognition +16

An Exploration of Dropout with LSTMs

Gaofeng Cheng, Vijayaditya Peddinti, Daniel Povey, +3

Sequence ModellingEngineeringMachine LearningData ScienceSpeech Processing +4

Online Hybrid CTC/Attention End-to-End Automatic Speech Recognition Architecture

Haoran Miao, Gaofeng Cheng, Pengyuan Zhang, +1

IEEE/ACM Transactions on Audio Speech and Language Processing

EngineeringMachine LearningSpoken Language ProcessingSpeech RecognitionNatural Language Processing +15

Online Hybrid CTC/Attention Architecture for End-to-End Speech Recognition

Haoran Miao, Gaofeng Cheng, Pengyuan Zhang, +2

EngineeringSpeech ProcessingComputer ScienceEnd-to-end Speech RecognitionSpeech Input +5

Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset

Zehui Yang, Yifan Chen, Lei Luo, +9

Interspeech 2022

EngineeringSpeech CorpusSpeech DatasetOpen Source Magicdata-ramcSpoken Language Processing +18

Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models

Keqi Deng, Songjun Cao, Yike Zhang, +4

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Llm Fine-tuningEngineeringMachine LearningSpoken Language ProcessingMultilingual Pretraining +21

Output-Gate Projected Gated Recurrent Unit for Speech Recognition

Gaofeng Cheng, Daniel Povey, Lu Huang, +3

EngineeringRobust Speech RecognitionSpeech ProcessingComputer ScienceSpeech Input +5

Keyword Search Using Attention-Based End-to-End ASR and Frame-Synchronous Phoneme Alignments

Runyan Yang, Gaofeng Cheng, Haoran Miao, +3

IEEE/ACM Transactions on Audio Speech and Language Processing

EngineeringMachine LearningFrame-synchronous Phoneme AlignmentsSpoken Language ProcessingCorpus Linguistics +22

ETEH: Unified Attention-Based End-to-End ASR and KWS Architecture

Gaofeng Cheng, Haoran Miao, Runyan Yang, +2

IEEE/ACM Transactions on Audio Speech and Language Processing