探索说话人识别数据集时要注意的问题

Grace_yanyanyan

于 2019-12-20 17:09:11 发布

阅读量413

点赞数

CC 4.0 BY-SA版权

分类专栏：学习笔记

本文链接：https://blog.youkuaiyun.com/yj13811596648/article/details/103635375

学习笔记专栏收录该内容

68 篇文章

订阅专栏

本文深入探讨了说话人识别社区中“训练”、“测试”和“发展”数据的不同使用方式，解释了这些术语与语音识别社区的区别。文章还讨论了i-vector训练中短语音的危害，以及在说话人识别系统开发中可能遇到的各种挑战，如跨信道、跨设备、跨距离的数据处理，性别比例不平衡，采样率、音量、语速等问题。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Note:
In the speaker id community the words “train”, “test” and “development”
are used in a different sense from in the speech recognition community. In
speaker-id land, the “development” data is the data you actually use to build
the system; the “training” and “test” data are really both used to test how
well the systme performs. The “training” data is used as enrolment data for a
particular speaker, and the evaluation consists of taking utterances from the
“test” data and having the system decide whether they were uttered by various
training speakers.（来自于kaldi/egs/sre08/v1/README.txt）

短语音对于i-vector的训练是有害的，小于100k的utterence都会被删除。（来自于kaldi/egs/sitw/v1）

enroll集和eval集可能有下面不同：