计算机与数字工程2019，Vol.47Issue(3)：493-496,4.DOI:10.3969/j.issn.1672-9722.2019.03.001
基于GRU-HMM声学模型的湖南方言辨识
Hunan Dialects Identification Based on GRU-HMM Acoustic Model
摘要
Abstract
An acoustic model based on Gated Recurrent Unit(GRU)neural networks and Hidden Markov Model(HMM)is established. The Mel-Frequency Cepstral Coefficients(MFCC)is used as the input of the acoustic model,and the GRU neural net?work can be used to perform the probability statistics on the speech data in real time. The obtained probability values are statistically re-evaluated by the HMM model. Finally the identification results are obtained. This method is used to identify the Hunan dialect. Experiments show that this acoustic model has better identification efficiency than the traditional acoustic model.关键词
门控循环单元(GRU)/隐马尔科夫模型(HMM)/声学模型/梅尔倒谱系数(MFCC)/湖南方言辨识Key words
gated recurrent unit(GRU)/hidden markov Model(HMM)/acoustic model/mel-frequency cepstral coeffi⁃cients(MFCC)/Hunan dialect identification分类
信息技术与安全科学引用本文复制引用
谢可欣,董胡,邹孝,汤琛,钱盛友..基于GRU-HMM声学模型的湖南方言辨识[J].计算机与数字工程,2019,47(3):493-496,4.基金项目
国家自然科学基金项目(编号:11474090,11774088) （编号:11474090,11774088）
湖南省教育厅优秀青年基金项目(编号:17B025) （编号:17B025）
湖南省自然科学青年基金项目(编号:2018JJ3557)资助. （编号:2018JJ3557）
