首页> 外文会议>Machine learning for multimodal interaction >Technical Improvements of the E-HMM Based Speaker Diarization System for Meeting Records
【24h】

Technical Improvements of the E-HMM Based Speaker Diarization System for Meeting Records

机译:基于E-HMM的会议记录说话人差异化系统的技术改进

获取原文
获取原文并翻译 | 示例

摘要

This paper is concerned with the speaker diarization task in the specific context of the meeting room recordings. Firstly, different technical improvements of an E-HMM based system are proposed and evaluated in the framework of the NIST RT'06S evaluation campaign. Related experiments show an absolute gain of 6.4% overall speaker diarization error rate (DER) and 12.9% on the development and evaluation corpora respectively.rnSecondly, this paper presents an original strategy to deal with the overlapping speech. Indeed, speech overlaps between speakers are largely involved in meetings due to the spontaneous nature of this kind of data and they are responsible for a decrease in performance of the speaker diarization system, if they are not dealt with. Experiments still conducted in the framework of the NIST RT'06S evaluation show the ability of the strategy in detecting overlapping speech (decrease of the missed speaker error rate), even if an overall gain in speaker diarization performance has not been achieved yet.
机译:本文与会议室录音的特定上下文中的说话人区分任务有关。首先,在NIST RT'06S评估活动的框架内,提出并评估了基于E-HMM的系统的不同技术改进。相关实验表明,在开发和评估语料库上,总体说话者二值化误差率(DER)的绝对增益分别为6.4%和12.9%。其次,本文提出了一种应对重叠语音的原始策略。确实,由于此类数据的自发性,演讲者之间的语音重叠在很大程度上参与了会议,如果不加以处理,它们将导致演讲者差异化系统性能下降。在NIST RT'06S评估框架内仍进行的实验表明,该策略具有检测重叠语音(降低说话者误码率的能力)的能力,即使尚未实现说话者分辨性能的整体提高。

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