...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Acoustics >Correlation distance skip connection denoising autoencoder (CDSK-DAE) for speech feature enhancement
【24h】

Correlation distance skip connection denoising autoencoder (CDSK-DAE) for speech feature enhancement

机译：用于语音功能增强的相关距离跳过连接去噪自动编码器（CDSK-DAE）

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise robust end-to-end ASR system by introducing a novel variant of denoising autoencoder (DAE). The proposed method uses skip connections in both encoder and decoder sides by passing speech information of the target frame from input to the model. It also uses a new objective function in training model that uses a correlation distance measure in penalty terms by measuring dependency of the latent target features and the model (latent features and enhanced features obtained from the DAE). Performance of the proposed method was compared against a conventional model and a state of the art model under both seen and unseen noisy environments of 7 different types of background noise with different SNR levels (0, 5, 10 and 20 dB). The proposed method also is tested using linear and non-linear penalty terms as well, where, they both show an improvement on the overall average WER under noisy conditions both seen and unseen in comparison to the state-of-the-art model. (C) 2020 Elsevier Ltd. All rights reserved.
机译：基于学习的自动语音识别（ASR）的性能容易受到噪声的影响，尤其是在将其引入测试数据中而未在训练数据中呈现时。这项工作的重点是通过引入新颖的降噪自动编码器（DAE）来增强抗噪声鲁棒端到端ASR系统的功能。所提出的方法通过将目标帧的语音信息从输入传递到模型来在编码器和解码器端使用跳过连接。它还在训练模型中使用了新的目标函数，该函数通过测量潜在目标特征和模型（从DAE获得的潜在特征和增强特征）之间的依赖性，以惩罚性术语使用了相关距离度量。将所提方法的性能与常规模型和现有技术模型在7种不同类型背景噪声（具有0、5、10和20 dB）的可见和不可见噪声环境下进行了比较。所提出的方法还使用线性和非线性惩罚项进行了测试，与现有技术模型相比，它们在可见和不可见的嘈杂条件下均显示出整体平均WER的改善。 （C）2020 Elsevier Ltd.保留所有权利。

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