Highway Long Shortterm Memory Rnns For Distant Speech Recognition

# Highway Long Short-Term Memory RNNs for Distant Speech Recognition

**arXiv ID:** 1510.08983
**Authors:** Yu Zhang, Guoguo Chen, Dong Yu, Kaisheng Yao, Sanjeev Khudanpur, James Glass
**Published:** 2015-10-30T06:40:14Z
**Abstract:**
In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded information flow across different layers and thus alleviate the gradient vanishing problem when building deeper LSTMs. We further introduce the latency-controlled bidirectional LSTMs (BLSTMs) which can exploit the whole history while keeping the latency under control. Efficient algorithms are proposed to train these novel networks using both frame and sequence discriminative criteria. Experiments on the AMI distant speech recognition (DSR) task indicate that we can train deeper LSTMs and achieve better improvement from sequence training with highway LSTMs (HLSTMs). Our novel model obtains $43.9/47.7\%$ WER on AMI (SDM) dev and eval sets, outperforming all previous works. It beats the strong DNN and DLSTM baselines with $15.7\%$ and $5.3\%$ relative improvement respectively.

## Skill Description

This skill is generated from the arXiv paper: Highway Long Short-Term Memory RNNs for Distant Speech Recognition (1510.08983).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1510.08983](http://arxiv.org/abs/1510.08983v2)