Improving Layer Trajectory LSTM with Future Context Frames
Lists
Only you see this
Abstract
In our recent work, we proposed a layer trajectory long short-term memory (ltLSTM) model which decouples the tasks of temporal modeling and senone classification with time-LSTMs and depth-LSTMs. The ltLSTM model achieved significant accuracy improvement over the traditional multi-layer LSTM models from our previous study. Considering the future context frames carrying valuable information for predicting the target label evidenced by the success of bi-directional LSTMs, in this work we investigate how to incorporate this kind of information with hidden vectors from either time-LSTM or depth-LSTM. Trained with 30 thousand hours of EN-US Microsoft internal data, the best ltLSTM model with future context frames can improve the baseline ltLSTM with up to 11.5% relative word error rate (WER) reduction and improve the baseline LSTM with up to 24.6% relative WER reduction across different tasks.
BibTeX
@inproceedings{li2019improving,
author = {Jinyu Li and Liang Lu and Changliang Liu and Yifan Gong},
title = {{Improving Layer Trajectory LSTM with Future Context Frames}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2019},
doi = {10.1109/icassp.2019.8683783},
}Loading related content...