Author Info
Name
Affiliation
Papers
YE BAI
National Laboratory of Pattern Recognition, Chinese Academy of Sciences, Beijing, China
16
Collaborators
Citations 
PageRank 
25
7
5.52
Referers 
Referees 
References 
31
95
18
Title
Citations
PageRank
Year
Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition00.342022
ADD 2022: the first Audio Deep Synthesis Detection Challenge.00.342022
Continual Learning for Fake Audio Detection.10.362021
Half-Truth - A Partially Fake Audio Detection Dataset.00.342021
DECOUPLING PRONUNCIATION AND LANGUAGE FOR END-TO-END CODE-SWITCHING AUTOMATIC SPEECH RECOGNITION00.342021
FSR - Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization.00.342021
Focal Loss for Punctuation Prediction.00.342020
Self-Attention Transducers for End-to-End Speech Recognition10.362019
A Time Delay Neural Network with Shared Weight Self-Attention for Small-Footprint Keyword Spotting00.342019
Language-Invariant Bottleneck Features From Adversarial End-To-End Acoustic Models For Low Resource Speech Recognition00.342019
Language-Adversarial Transfer Learning for Low-Resource Speech Recognition.30.392019
Voice Activity Detection Based on Time-Delay Neural Networks10.352019
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition10.342019
CLMAD: A Chinese Language Model Adaptation Dataset00.342018
Utterance-level Permutation Invariant Training with Discriminative Learning for Single Channel Speech Separation00.342018
End-to-end keywords spotting based on connectionist temporal classification for Mandarin00.342016