• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Federated Conference on Computer Science and Information Systems >Evaluation of methods to combine different speech recognizers
【24h】

Evaluation of methods to combine different speech recognizers

机译：评估组合不同语音识别器的方法

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

摘要

The paper deals with the problem of improving speech recognition by combining outputs of several different recognizers. We are presenting our results obtained by experimenting with different classification methods which are suitable to combine outputs of different speech recognizers. Methods which were evaluated are: k-Nearest neighbors (KNN), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Logistic Regression (LR) and maximum likelihood (ML). Results showed, that highest accuracy (98.16 %) was obtained when k-Nearest neighbors method was used with 15 nearest neighbors. In this case accuracy was increased by 7.78 % compared with best single recognizer result. In our experiments we tried to combine one native (Lithuanian language) and few foreign speech recognizers: Russian, English and two German recognizers. For the adaptation of foreign language speech recognizers we used text transcribing method which is based on formal rules. Our experiments proved, that recognition accuracy improves when few speech recognizers are combined.
机译：本文讨论了通过组合几种不同的识别器的输出来改善语音识别的问题。我们将介绍通过试验不同分类方法而获得的结果，这些方法适用于组合不同语音识别器的输出。评估的方法是：k最近邻（KNN），线性判别分析（LDA），二次判别分析（QDA），逻辑回归（LR）和最大似然（ML）。结果表明，与15个最近邻居一起使用k-最近邻居方法可获得最高的准确性（98.16％）。在这种情况下，与最佳单一识别器结果相比，准确性提高了7.78％。在我们的实验中，我们尝试结合一种母语（立陶宛语）和很少的外语识别器：俄语，英语和两个德语识别器。为了适应外语语音识别器，我们使用了基于形式规则的文本转录方法。我们的实验证明，当很少的语音识别器组合在一起时，识别精度会提高。

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