Ensemble Of Gaussian Mixture Localized Neural Networks With Application To Phone Recognition
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5(2015)
摘要
In this paper we present Ensemble of Gaussian Mixture Localized Neural Networks (EGMLNNs), a model for the joint probability density of input as well as output variables of any general mapping to be estimated. The model aims at identifying clusters in the input data, thereby replacing one complex classifier with an ensemble of relatively simpler classifiers, each of which is localized to operate within its associated cluster. We present an algorithm for maximum likelihood parameter estimation for this model using Expectation Maximization (EM). The reported results on phone recognition task on TIMIT database show that the model is able to obtain performance improvement over a single complex classifier while also reducing the computational complexity required for testing.
更多查看译文
关键词
Neural Networks, Acoustic Modeling, Speech Recognition, Phone Recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络