首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Simplifying long short-term memory acoustic models for fast training and decoding
【24h】

Simplifying long short-term memory acoustic models for fast training and decoding

机译:简化长短期记忆声学模型以进行快速训练和解码

获取原文

摘要

On acoustic modeling, recurrent neural networks (RNNs) using Long Short-Term Memory (LSTM) units have recently been shown to outperform deep neural networks (DNNs) models. This paper focuses on resolving two challenges faced by LSTM models: high model complexity and poor decoding efficiency. Motivated by our analysis of the gates activation and function, we present two LSTM simplifications: deriving input gates from forget gates, and removing recurrent inputs from output gates. To accelerate decoding of LSTMs, we propose to apply frame skipping during training, and frame skipping and posterior copying (FSPC) during decoding. In the experiments, model simplifications reduce the size of LSTM models by 26%, resulting in a simpler model structure. Meanwhile, the application of FSPC speeds up model computation by 2 times during LSTM decoding. All these improvements are achieved at the cost of 1% WER degradation.
机译:在声学建模方面,最近显示使用长短期记忆(LSTM)单元的递归神经网络(RNN)优于深度神经网络(DNN)模型。本文着重解决LSTM模型面临的两个挑战:模型复杂度高和解码效率低。通过对门的激活和功能的分析,我们提出了两种LSTM简化方法:从忘记门派生输入门,从输出门中删除递归输入。为了加速LSTM的解码,我们建议在训练过程中应用跳帧,并在解码过程中应用跳帧和后向复制(FSPC)。在实验中,模型简化使LSTM模型的大小减少了26%,从而简化了模型结构。同时,FSPC的应用在LSTM解码期间将模型计算速度提高了2倍。所有这些改进都是以WER降低1%的代价实现的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号