Continuous Hindi Speech Recognition Using Kaldi ASR Based on Deep Neural Network

被引：7

作者：

Upadhyaya, Prashant ^{[1
]}

Mittal, Sanjeev Kumar ^{[2
]}

Farooq, Omar ^{[1
]}

Varshney, Yash Vardhan ^{[1
]}

Abidi, Musiur Raza ^{[1
]}

机构：

[1] Aligarh Muslim Univ, Dept Elect, Aligarh 202002, Uttar Pradesh, India

[2] Indian Inst Sci Bangalore, Elect Engn, Bengaluru 560012, Karnataka, India

来源：

MACHINE INTELLIGENCE AND SIGNAL ANALYSIS | 2019年 / 748卷

关键词：

Deep neural network (DNN); Hidden markov model (HMM); Speech recognition; Kaldi; Hindi language;

D O I：

10.1007/978-981-13-0923-6_26

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Today, deep learning is one of the most reliable and technically equipped approaches for developing more accurate speech recognition model and natural language processing (NLP). In this paper, we propose Context-Dependent Deep Neural-network HMMs (CD-DNN-HMM) for large vocabulary Hindi speech using Kaldi automatic speech recognition toolkit. Experiments on AMUAV database demonstrate that CD-DNN-HMMs outperform the conventional CD-GMM-HMMs model and provide the improvement in word error rate of 3.1% over conventional triphone model.

引用

页码：303 / 311

页数：9

共 50 条

[1] Continuous Hindi Speech Recognition Model Based on Kaldi ASR Toolkit
Upadhyaya, Prashant
Farooq, Omar
Abidi, Musiur Raza
Varshney, Yash Vardhan
[J]. 2017 2ND IEEE INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), 2017, : 786 - 789
[2] Deep Neural Network Based Continuous Speech Recognition for Serbian Using the Kaldi Toolkit
Popovic, Branislav
Ostrogonac, Stevan
Pakoci, Edvin
Jakovljevic, Niksa
Delic, Vlado
[J]. SPEECH AND COMPUTER (SPECOM 2015), 2015, 9319 : 186 - 192
[3] Continuous Punjabi speech recognition model based on Kaldi ASR toolkit
Guglani, Jyoti
Mishra, A. N.
[J]. INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2018, 21 (02) : 211 - 216
[4] Amazigh speech recognition based on the Kaldi ASR toolkit
Barkani F.
Hamidi M.
Laaidi N.
Zealouk O.
Satori H.
Satori K.
[J]. International Journal of Information Technology, 2023, 15 (7) : 3533 - 3540
[5] Speaker Adaptive Model for Hindi Speech using Kaldi Speech Recognition toolkit
Upadhyaya, Prashant
Mittal, Sanjeev Kumar
Varshney, Yash Vardhan
Farooq, Omar
Abidi, Musiur Raza
[J]. PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON MULTIMEDIA, SIGNAL PROCESSING AND COMMUNICATION TECHNOLOGIES (IMPACT), 2017, : 222 - 226
[6] Development of Hindi speech recognition system of agricultural commodities using deep neural network
Mandal, Partho
Jain, Shalini
Ojha, Gaurav
Shukla, Anupam
[J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1241 - 1245
[7] Deep Neural Network Frontend for Continuous EMG-based Speech Recognition
Wand, Michael
Schmidhuber, Jurgen
[J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3032 - 3036
[8] Discriminatively trained continuous Hindi speech recognition system using interpolated recurrent neural network language modeling
Mohit Dua
R. K. Aggarwal
Mantosh Biswas
[J]. Neural Computing and Applications, 2019, 31 : 6747 - 6755
[9] Hindi Handwritten Character Recognition using Deep Convolution Neural Network
Chaudhary, Deepak
Sharma, Kaushal
[J]. PROCEEDINGS OF THE 2019 6TH INTERNATIONAL CONFERENCE ON COMPUTING FOR SUSTAINABLE GLOBAL DEVELOPMENT (INDIACOM), 2019, : 961 - 965
[10] Discriminatively trained continuous Hindi speech recognition system using interpolated recurrent neural network language modeling
Dua, Mohit
Aggarwal, R. K.
Biswas, Mantosh
[J]. NEURAL COMPUTING & APPLICATIONS, 2019, 31 (10): : 6747 - 6755

← 1 2 3 4 5 →