Stabilising and accelerating light gated recurrent units for automatic speech recognition

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2023)

Cited 0|Views14
No score
Abstract
The light gated recurrent units (Li-GRU) is well-known for achieving impressive results in automatic speech recognition (ASR) tasks while being lighter and faster to train than a standard gated recurrent units (GRU). However, the unbounded nature of its rectified linear unit on the candidate recurrent gate induces an important gradient exploding phenomenon disrupting the training process and preventing it from being applied to famous datasets. In this paper, we theoretically and empirically derive the necessary conditions for its stability as well as engineering mechanisms to speed up by a factor of five its training time, hence introducing a novel version of this architecture named SLi-GRU. Then, we evaluate its performance both on a toy task illustrating its newly acquired capabilities and a set of three different ASR datasets demonstrating lower word error rates compared to more complex recurrent neural networks.
More
Translated text
Key words
recurrent units,speech,recognition
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined