• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Bridgenets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and Its Application to Distant Speech Recognition
【24h】

Bridgenets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and Its Application to Distant Speech Recognition

机译：Bridgenets：基于递归神经网络的学生 - 教师转移学习及其在遥远语音识别中的应用

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Despite the remarkable progress achieved on automatic speech recognition, recognizing far-field speeches mixed with various noise sources is still a challenging task. In this paper, we introduce novel student-teacher transfer learning, BridgeNet which can provide a solution to improve distant speech recognition. There are two key features in BridgeNet. First, BridgeNet extends traditional student-teacher frameworks by providing multiple hints from a teacher network. Hints are not limited to the soft labels from a teacher network. Teacher's intermediate feature representations can better guide a student network to learn how to denoise or dereverberate noisy input. Second, the proposed recursive architecture in the BridgeNet can iteratively improve denoising and recognition performance. The experimental results of BridgeNet showed significant improvements in tackling the distant speech recognition problem, where it achieved up to 13.24% relative WER reductions on AMI corpus compared to a baseline neural network without teacher's hints.
机译：尽管在自动演讲中实现了显着进展，但识别与各种噪声源混合的远场演示仍然是一个具有挑战性的任务。在本文中，我们介绍了新的学生 - 教师转移学习，Bridgenet，可以提供改善遥远语音识别的解决方案。 Bridgenet中有两个主要功能。首先，BridGanet通过从教师网络提供多个提示来扩展传统的学生教师框架。提示不限于来自教师网络的软标签。教师的中间特征表示可以更好地指导学生网络来学习如何登记或DeReverberate Noisy输入。其次，BridGanet中提出的递归架构可以迭代地改善去噪和识别性能。 Bridgenet的实验结果表明，解决遥感语音识别问题的显着改进，而在没有教师提示的基线神经网络相比，AMI语料库的相对WER减少高达13.24％。

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