Component Fusion: Learning Replaceable Language Model Component for End-to-end Speech Recognition System
Lists
Only you see this
Abstract
Recently, attention-based end-to-end automatic speech recognition system (ASR) has shown promising results. One of the limitations of an attention-based ASR system is that its language model (LM) component has to be implicitly learned from transcribed speech data which prevents one from uti-lizing plenty of text corpora to improve language modeling. In this work, the Component Fusion method is proposed to incorporate externally trained neural network (NN) LM into an attention-based ASR system. During training stage we equip the attention-based system with an additional LM component which is replaced by an externally trained NN LM at decoding stage. Experimental results show that the proposed Component Fusion outperforms two prior LM fusion approaches, i.e., Shallow Fusion and Cold Fusion, in both out-of-domain and in-domain scenarios. Further improvements can be achieved when combining Component and Shallow Fusion.
BibTeX
@inproceedings{shan2019component,
author = {Changhao Shan and Chao Weng and Guangsen Wang and Dan Su and Min Luo and Dong Yu and Lei Xie},
title = {{Component Fusion: Learning Replaceable Language Model Component for End-to-end Speech Recognition System}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2019},
doi = {10.1109/icassp.2019.8682490},
}Loading related content...