• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Joint Conference on Neural Networks >Semi-supervised Training for Sequence-to-Sequence Speech Recognition Using Reinforcement Learning
【24h】

Semi-supervised Training for Sequence-to-Sequence Speech Recognition Using Reinforcement Learning

机译：使用强化学习的序列到序列语音识别的半监督训练

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

摘要

This paper proposes a reinforcement learning based semi-supervised training approach for sequence-to-sequence automatic speech recognition (ASR) systems. Most recent semi-supervised training approaches are based on multi-loss functions such as cross-entropy loss for speech-to-text paired data and reconstruction loss for speech-text unpaired data.Although these approaches show promising results, some considerations still remain: (a) different loss functions are used for paired and unpaired data separately even though the purpose is classification accuracy improvement, and (b) several methods need auxiliary networks that increase the complexity of a semi-supervised training process.To address these issues, a reinforcement learning based approach is proposed. The proposed approach focuses on rewarding ASR to generate more correct sentences for both paired and unpaired speech data. The proposed approach is evaluated on the Wall Street Journal task domain. The experimental results show that the proposed method is effective by reducing the character error rate from 10.4% to 8.7%.
机译：本文提出了一种用于序列到序列自动语音识别（ASR）系统的基于强化学习的半监督训练方法。最新的半监督训练方法基于多损失函数，例如语音-文本配对数据的交叉熵损失和语音-文本非配对数据的重建损失，尽管这些方法显示出令人鼓舞的结果，但仍需考虑以下因素： （a）不同的损失函数分别用于配对和未配对的数据，即使目的是提高分类精度，并且（b）几种方法需要辅助网络，这会增加半监督训练过程的复杂性。提出了基于强化学习的方法。提出的方法侧重于奖励ASR，以为配对和非配对的语音数据生成更正确的句子。建议的方法在《华尔街日报》的任务域中进行了评估。实验结果表明，该方法可以有效地将字符错误率从10.4％降低到8.7％。

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