Incorporating Language Level Information into Acoustic Models
Computation and Language
2020-11-12 v2 Machine Learning
Sound
Abstract
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.
Cite
@article{arxiv.1612.04744,
title = {Incorporating Language Level Information into Acoustic Models},
author = {Peidong Wang and Deliang Wang},
journal= {arXiv preprint arXiv:1612.04744},
year = {2020}
}
Comments
The project was discontinued