Mongolian Speech Recognition Based on Deep Neural Networks

被引：7

作者：

Zhang, Hui ^{[1
]}

Bao, Feilong ^{[1
]}

Gao, Guanglai ^{[1
]}

机构：

[1] Inner Mongolia Univ, Coll Comp Sci, Hohhot 010021, Peoples R China

来源：

CHINESE COMPUTATIONAL LINGUISTICS AND NATURAL LANGUAGE PROCESSING BASED ON NATURALLY ANNOTATED BIG DATA (CCL 2015) | 2015年 / 9427卷

关键词：

Mongolian; Deep Neural Networks (DNNs); Gaussian Mixture Models (GMMs); N-gram language model;

D O I：

10.1007/978-3-319-25816-4_15

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Mongolian is an influential language. And better Mongolian Large Vocabulary Continuous Speech Recognition (LVCSR) systems are required. Recently, the research of speech recognition has achieved a big improvement by introducing the Deep Neural Networks (DNNs). In this study, a DNN-based Mongolian LVCSR system is built. Experimental results show that the DNN-based models outperform the conventional models which based on Gaussian Mixture Models (GMMs) for the Mongolian speech recognition, by a large margin. Compared with the best GMM-based model, the DNN-based one obtains a relative improvement over 50 %. And it becomes a new state-of-the-art system in this field.

引用

页码：180 / 188

页数：9

共 50 条

[1] Acceleration Strategies for Speech Recognition based on Deep Neural Networks
Tian, Chao
Liu, Jia
Peng, Zhaomeng
[J]. MECHATRONICS ENGINEERING, COMPUTING AND INFORMATION TECHNOLOGY, 2014, 556-562 : 5181 - 5185
[2] DEEP MAXOUT NEURAL NETWORKS FOR SPEECH RECOGNITION
Cai, Meng
Shi, Yongzhe
Liu, Jia
[J]. 2013 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2013, : 291 - 296
[3] Deep Segmental Neural Networks for Speech Recognition
Abdel-Hamid, Ossama
Deng, Li
Yu, Dong
Jiang, Hui
[J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 1848 - 1852
[4] Deep Neural Networks in Russian Speech Recognition
Markovnikov, Nikita
Kipyatkova, Irina
Karpov, Alexey
Filchenkov, Andrey
[J]. ARTIFICIAL INTELLIGENCE AND NATURAL LANGUAGE, 2018, 789 : 54 - 67
[5] Binary Deep Neural Networks for Speech Recognition
Xiang, Xu
Qian, Yanmin
Yu, Kai
[J]. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 533 - 537
[6] SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS
Graves, Alex
Mohamed, Abdel-rahman
Hinton, Geoffrey
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 6645 - 6649
[7] Automatic Speech Recognition with Deep Neural Networks for Impaired Speech
Espana-Bonet, Cristina
Fonollosa, Jose A. R.
[J]. ADVANCES IN SPEECH AND LANGUAGE TECHNOLOGIES FOR IBERIAN LANGUAGES, IBERSPEECH 2016, 2016, 10077 : 97 - 107
[8] Robust Speech Recognition with Speech Enhanced Deep Neural Networks
Du, Jun
Wang, Qing
Gao, Tian
Xu, Yong
Dai, Lirong
Lee, Chin-Hui
[J]. 15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 616 - 620
[9] Exploiting deep neural networks for detection-based speech recognition
Siniscalchi, Sabato Marco
Yu, Dong
Deng, Li
Lee, Chin-Hui
[J]. NEUROCOMPUTING, 2013, 106 : 148 - 157
[10] Improvement on Speech Emotion Recognition Based on Deep Convolutional Neural Networks
Niu, Yafeng
Zou, Dongsheng
Niu, Yadong
He, Zhongshi
Tan, Hua
[J]. PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON COMPUTING AND ARTIFICIAL INTELLIGENCE (ICCAI 2018), 2018, : 13 - 18

← 1 2 3 4 5 →