首页 | 本学科首页   官方微博 | 高级检索  
     

深度学习在语音识别中的研究进展综述
引用本文:侯一民,周慧琼,王政一.深度学习在语音识别中的研究进展综述[J].计算机应用研究,2017,34(8).
作者姓名:侯一民  周慧琼  王政一
作者单位:东北电力大学自动化工程学院,东北电力大学自动化工程学院,中国航空规划设计研究总院有限公司
基金项目:国家自然科学基金项目(61403075);吉林省科技发展计划项目(20150414051GH)
摘    要:在如今的大数据时代里,对于处理大量未经标注的原始语音数据的传统机器学习算法,很多都已不再适用。与此同时,深度学习模型凭借着其对海量数据的强大建模能力,能够直接对未标注数据进行处理,成为当前语音识别领域的一个研究热点。首先主要分析和总结了当前几种具有代表性的深度学习模型;其次是其在语音识别中对于语音特征提取及声学建模中的应用;最后总结了当前所面临的问题和发展方向。

关 键 词:机器学习  深度学习  语音数据  语音识别
收稿时间:2016/9/19 0:00:00
修稿时间:2017/4/11 0:00:00

Research to speech Recognition Based on deep learning
HOU Yi-min,ZHOU Hui-qiong and WANG Zheng-yi.Research to speech Recognition Based on deep learning[J].Application Research of Computers,2017,34(8).
Authors:HOU Yi-min  ZHOU Hui-qiong and WANG Zheng-yi
Affiliation:School of automation Engineering,Northeast Dianli University,Jilin Province,Jilin,,
Abstract:In the era of big data, many of traditional machine learning methods of disposing unlabeled raw voice data have become less applicable.At the same time, deep learning models can directly process unlabeled data because of its powerful capability of modeling to deal with the massive data, and has become a hot research in the field of speech recognition.To begin with, this paper analyzes and summarizes the state-of-the-art deep learning of models.And then,it discussed the applications to speech recognition with speech features extraction and acoustic modeling. Finally,it concluded the problems faced and development orientation.
Keywords:Machine Learning  Deep Learning  Voice Data  Speech Recognition
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号