A technique to overcome the problem of small size database for automatic speaker recognition

机译：一种克服自动扬声器识别小尺寸数据库问题的技术

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Modeling a system by statistical methods needs large amount of data to train the system. In real life such data are sometimes not available or hard to collect. Modeling the system with small size database will produce a system with poor performance. In this paper we propose a method for increasing the size of the database. The method works by generating new samples from the original samples, using combinations of the following methods: speech lengthening, noise adding, and word reversal. To make a proof of concept, we used a severe test condition, in which the original database consists of one sample per speaker, for a speaker recognition system. We tested the system using original samples. The best results were 90% and 90.41% recognition rates for two subsets of the database for 25 and 50 speakers respectively.

机译：通过统计方法建模系统需要大量数据来训练系统。在现实生活中，这些数据有时不可用或难以收集。使用小尺寸数据库建模系统将产生具有差的性能差的系统。在本文中，我们提出了一种增加数据库大小的方法。该方法通过使用以下方法的组合生成新的样本来生成新样本：语音纵横，噪声添加和单词反转。为了制定概念证明，我们使用了严重的测试条件，其中原始数据库由每个扬声器的一个样本组成，用于扬声器识别系统。我们使用原始样品测试了系统。最佳结果分别为25和50个发言者的两个子集的识别率为90％和90.41％。

著录项

来源
《International Conference on Digital Information Management》|2010年||共6页
会议地点
作者
{missing};
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 TP18-53;
关键词

相似文献

外文文献
中文文献
专利

1. A technique to overcome the problem of small size database for automatic speaker recognition [J] . Mansour Alsulaiman International Journal of Physical Sciences . 2012,第13期

机译：克服小型数据库自动说话人识别问题的技术
2. On the design of automatic voice condition analysis systems. Part Ⅱ: Review of speaker recognition techniques and study on the effects of different variability factors [J] . Gomez-Garcia J. A., Moro-Velazquez L., Godino-Llorente J. I. Biomedical signal processing and control . 2019,第FEBa期

机译：关于语音条件自动分析系统的设计。第二部分：说话人识别技术综述及不同变异因素的影响研究
3. Assessment of Severe Apnoea through Voice Analysis,Automatic Speech, and Speaker Recognition Techniques [J] . Ruben Fernandez Pozo, Jose Luis Blanco Murillo, Luis Hernandez Gomez, EURASIP journal on advances in signal processing . 2009,第10期

机译：通过语音分析，自动语音和说话人识别技术评估严重呼吸暂停
4. A technique to overcome the problem of small size database for automatic speaker recognition [C] . Fifth International Conference on Digital Information Management . 2010

机译：克服小型数据库自动说话人识别问题的技术
5. A multimodal fusion approach for automatic postal address recognition system using Optical Character Recognition (OCR) and Automatic Speech Recognition (ASR) techniques. [D] . Singh, Amriteshwar. 2011

机译：一种使用光学字符识别（OCR）和自动语音识别（ASR）技术的自动邮政地址识别系统的多模式融合方法。
6. Non-heuristic automatic techniques for overcoming low signal-to-noise-ratio bias of localization microscopy and multiple signal classification algorithm [O] . Krishna Agarwal, Radek Macháň, Dilip K. Prasad -1

机译：克服定位显微镜低信噪比偏差和多信号分类算法的非启发式自动技术
7. On the design of automatic voice condition analysis systems. Part II: Review of speaker recognition techniques and study on the effects of different variability factors [O] . J.A. Gómez-García, L. Moro-Velázquez, J.I. Godino-Llorente 2019

机译：关于自动语音条件分析系统的设计。第二部分：讲话者识别技术审查和不同变异因素影响的研究

A technique to overcome the problem of small size database for automatic speaker recognition

摘要

著录项

相似文献

相关主题

期刊订阅