首页> 外文会议>International Speech Communication Association >Maximum Mutual Information Estimation with Unlabeled Datafor Phonetic Classification
【24h】

Maximum Mutual Information Estimation with Unlabeled Datafor Phonetic Classification

机译:使用未标记数据进行语音分类的最大互信息估算

获取原文

摘要

This paper proposes a new training framework for mixed la-beled and unlabeled data and evaluates it on the task of binary phonetic classification. Our training objective function com-bines Maximum Mutual Information (MMI) for labeled data and Maximum Likelihood (ML) for unlabeled data. Through the modified training objective, MMI estimates are smoothed with ML estimates obtained from unlabeled data. On the other hand, our training criterion can also help the existing model adapt to new speech characteristics from unlabeled speech. In our experiments of phonetic classification, there is a consistent reduction of error rate from MLE to MMIE with I-smoothing, and then to MMIE with unlabeled-smoothing. Error rates can be further reduced by transductive-MMIE. We also experimented with the gender-mismatched case, in which the best improve-ment shows MMIE with unlabeled data has a 9.3% absolute lower error rate than MLE and a 2.35% absolute lower error rate than MMIE with I-smoothing.
机译:本文为混合洛杉矶和未标记的数据提出了新的培训框架,并在二进制语音分类的任务上评估它。我们的训练目标函数Com-Bines最大互信息(MMI),用于标记数据和用于未标记数据的最大可能性(ML)。通过修改的训练目标,MMI估计用来自未标记数据获得的ML估计进行平滑。另一方面,我们的训练标准还可以帮助现有模型适应来自未标记语音的新语音特征。在我们的语音分类的实验中,使用I光滑的MLE到MMIE的错误率降低,然后用未标记平滑的MMIE。通过Transtonuctive-MMIE可以进一步减少错误率。我们还试验了性别不匹配的情况,其中最佳改进的案件显示了具有未标记数据的MMIE,其绝对值低于MLE,比MLE更低的误差率和2.35%的误差率比MMIE更低,具有I光滑。

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