Speaker identification using neural networks and wavelets
Speaker identification using neural networks and wavelets
复制标题
使用神经网络和小波进行说话人识别
DOI：
--
复制
发表时间：
2000
影响因子：
--
通讯作者：
S. Sideman
中科院分区：
文献类型：
--
作者：
F. Phan;Evangelia Micheli;S. Sideman
多分辨率分解和模式识别技术可以在嘈杂的环境中进行识别。“鸡尾酒会”效应描述了人类可以选择性地将注意力集中到竞争声源中的一个声源的现象。这是一个能力，是阻碍听力受损的人。在这篇文章中，作者提出了一个离线系统，使用小波来生成多分辨率的时间-频率特征，其特征在于语音波形，成功地识别扬声器中存在的竞争扬声器。该系统在短语音识别中取得了成功，并已应用于说话人间语音识别。作者还讨论了ALOPEX，这是一种优化范式，通过在前馈人工神经网络中进行模板匹配或连接权重更新，将上述特征纳入模式识别系统。
Multiresolution decomposition and pattern-recognition techniques enable identification in noisy environments. The "cocktail party" effect describes the phenomenon in which humans can selectively focus attention to one sound source among competing sound sources. This is an ability that is hampered for hearing-impaired individuals. In this article, the authors present an off-line system that uses wavelets to generate multiresolution time-frequency features that characterize the speech waveform to successfully identify a speaker in the presence of competing speakers. This system is successful for short utterances and has also been applied to interspeaker speech recognition. The authors also discuss ALOPEX, which is an optimization paradigm that incorporates the above-mentioned features into a pattern-recognition system through template matching or connectivity weight updating in a feedforward artificial neural network.
数字助听器：教程回顾。
影响因子：
--
作者：
Levitt,H
通讯作者：
Levitt,H