End-to-End Mandarin Speech Recognition Combining CNN and BLSTM

End-to-End Mandarin Speech Recognition Combining CNN and BLSTM

Since conventional Automatic Speech Recognition (ASR) systems often contain many modules and use varieties of expertise, it is hard to build and train such models. Recent research show that end-to-end ASRs can significantly simplify the speech recognition pipelines and achieve competitive performanc...

Full description

Bibliographic Details
Main Authors: Dong Wang, Xiaodong Wang, Shaohe Lv
Format: Article
Language:English
Published: MDPI AG 2019-05-01
Series:Symmetry
Subjects:
automatic speech recognition
end-to-end model
deep learning
convolution
bidirectional LSTM
connectionist temporal classification
Mandarin speech recognition
Online Access:https://www.mdpi.com/2073-8994/11/5/644

Internet

https://www.mdpi.com/2073-8994/11/5/644

Similar Items