Incorporating Language Level Information into Acoustic Models

12/14/2016
by   Peidong Wang, et al.
0

This paper proposed a class of novel Deep Recurrent Neural Networks which can incorporate language-level information into acoustic models. For simplicity, we named these networks Recurrent Deep Language Networks (RDLNs). Multiple variants of RDLNs were considered, including two kinds of context information, two methods to process the context, and two methods to incorporate the language-level information. RDLNs provided possible methods to fine-tune the whole Automatic Speech Recognition (ASR) system in the acoustic modeling process.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset