||
本文为美国卡耐基梅隆大学(作者:Emanuel Jöbstl)的硕士论文,共73页。
本文研究了基于隐马尔可夫模型的鲁棒声学建模,用于语音识别系统。本文的工作重点是时延神经网络。我们首先设计了一个用于声学建模的时延神经网络模型,并给出了实验结果,证明了我们对设计参数的选择是正确的。然后,我们在增广数据上训练时延神经网络,并将其与传统的全连接神经网络在混响数据上的性能进行了比较。
This work investigates robust acoustic modeling for speech recognition systems based on hidden Markov models. The focus of this work is put on time delay neural networks. We first design a time delay neural network model for acoustic modeling and provide empirical results that justify our choice of design parameters. Then, we train the time delay neural network on augmented data, and compare its performance on reverberated data with conventional fully connected neural networks.
Archiver|手机版|科学网 ( 京ICP备07017567号-12 )
GMT+8, 2024-9-24 20:19
Powered by ScienceNet.cn
Copyright © 2007- 中国科学报社