首页> 外文期刊>Audio, Speech, and Language Processing, IEEE Transactions on >Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features
【24h】

Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features

机译:通过具有增强的培训和功能的数据采样来构建声学模型集合

获取原文
获取原文并翻译 | 示例

摘要

We propose a novel approach of using Cross Validation (CV) and Speaker Clustering (SC) based data samplings to construct an ensemble of acoustic models for speech recognition. We also investigate the effects of the existing techniques of Cross Validation Expectation Maximization (CVEM), Discriminative Training (DT), and Multiple Layer Perceptron (MLP) features on the quality of the proposed ensemble acoustic models (EAMs). We have evaluated the proposed methods on TIMIT phoneme recognition task as well as on a telemedicine automatic captioning task. The proposed methods have led to significant improvements in recognition accuracy over conventional Hidden Markov Model (HMM) baseline systems, and the integration of EAMs with CVEM, DT, and MLP has also significantly improved the accuracy performances of the single model systems based on CVEM, DT, and MLP, where the increased inter-model diversity is shown to have played an important role in the performance gain.
机译:我们提出一种使用基于交叉验证(CV)和说话者聚类(SC)的数据采样的新颖方法,以构建用于语音识别的声学模型的集成。我们还研究了交叉验证期望最大化(CVEM),判别训练(DT)和多层感知器(MLP)功能的现有技术对所提出的集成声学模型(EAM)质量的影响。我们已经评估了TIMIT音素识别任务以及远程医疗自动字幕任务的建议方法。与传统的隐马尔可夫模型(HMM)基准系统相比,提出的方法已大大提高了识别准确性,并且EAM与CVEM,DT和MLP的集成还显着提高了基于CVEM的单模型系统的准确性, DT和MLP,其中模型间多样性的增加在性能提升中起着重要作用。

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