Speech recognition using probabilistic and statistical models

被引:0
作者
Singh, Amber [1 ]
Anand, R. S. [1 ]
机构
[1] Indian Inst Technol, Dept Elect Engn, Roorkee, Uttar Pradesh, India
来源
2015 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMMUNICATION NETWORKS (CICN) | 2015年
关键词
Automatic speech recognition (ASR); Mel frequency cepstral coefficients (MFCCs); EM algorithm; Hidden markov model; Gaussian mixture model; Vector quantization; Gaussian mixture model-Universal background model;
D O I
10.1109/CICN.2015.141
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents an implementation of probabilistic and statistical models for speech recognition. Three models namely Gaussian mixture model, hidden markov model and Gaussian mixture model - universal background model are discussed. In GMM, both speech identification of unknown isolated words and classification of unknown test patterns are discussed. In HMM, speech identification of isolated words are discussed. In GMM-UBM, speech identification of isolated words and speech classification of unknown test patterns are discussed. Isolated word recognizer build using all the three models for the recognition of isolated words can give 100% accuracy depending upon the initialization of the models. GMM-UBM is not found suitable for the classification of unknown test patterns.
引用
收藏
页码:686 / 690
页数:5
相关论文
共 13 条
[1]  
[Anonymous], SIGNAL PROCESS
[2]  
[Anonymous], IEEE T PATTEN ANAL I, DOI DOI 10.1109/5.58325
[3]  
Brookes Mike., VOICEBOX: Speech Processing Toolbox for MATLAB
[4]  
Deller J. R., 2000, DISCRE TIME PROCESSI
[5]  
Linde, 1980, IEEE T COMMUNICATION
[6]  
Nema D., THESIS
[7]  
Rabiner L.R, 1978, DIGITAL PROCESSINGB
[8]   A TUTORIAL ON HIDDEN MARKOV-MODELS AND SELECTED APPLICATIONS IN SPEECH RECOGNITION [J].
RABINER, LR .
PROCEEDINGS OF THE IEEE, 1989, 77 (02) :257-286
[9]  
Rose R., 1995, IEEE T SPEECH AUDIO, V3, P72
[10]  
Rosenburg A.E, 1987, AT&T TECH J, V66, P14