Tree-structured model selection and simulated-data adaptation for environmental and speaker robust speech recognition

2007 ◽  
Author(s):  
Nattanun Thatphithakkul ◽  
Boontee Kruatrachue ◽  
Chai Wutiwiwatchai ◽  
Sanparith Marukatat ◽  
Vataya Boonpiam
Keyword(s):  
Speech Recognition ◽  
Model Selection ◽  
Simulated Data ◽  
Robust Speech Recognition ◽  
Structured Model

A simulated-data adaptation technique for robust speech recognition

2006 ◽  
Author(s):  
Nattanun Thatphithakkul ◽  
Boontee Kruatrachue ◽  
Chai Wutiwiwatchai ◽  
Sanparith Marukatat ◽  
Vataya Boonpiam
Keyword(s):  
Speech Recognition ◽  
Simulated Data ◽  
Robust Speech Recognition

scholarly journals SIMULATED-DATA ADAPTATION BASED PIECEWISE LINEAR TRANSFORMATION FOR ROBUST SPEECH RECOGNITION

2017 ◽  
Vol 24 (4) ◽  
pp. 339-352
Author(s):  
Nattanun Thatphithakkul ◽  
Boontee Kruatrachue ◽  
Chai Wutiwiwatchai ◽  
Sanparith Marukatat ◽  
Vataya Boonpiam
Keyword(s):  
Speech Recognition ◽  
Linear Transformation ◽  
Piecewise Linear ◽  
Recognition Rate ◽  
Simulated Data ◽  
Robust Speech Recognition ◽  
Adaptation Process ◽  
Acoustic Model ◽  
Piecewise Linear Transformation ◽  
Adaptation Data

This paper proposes an efficient method of simulated-data adaptation for robust speech recognition. The method is applied to tree-structured piecewise linear transformation (PLT). The original PLT selects an acoustic model using tree-structured HMMs and the acoustic model is adapted by input speech in an unsupervised scheme. This adaptation can degrade the acoustic model if the input speech is incorrectly transcribed during the adaptation process. Moreover, adaptation may not be effective if only the input speech is used. Our proposed method increases the size of adaptation data by adding noise portions from the input speech to a set of prerecorded clean speech, of which correct transcriptions are known. We investigate various configurations of the proposed method. Evaluations are performed with both additive and real noisy speech. The experimental results show that the proposed system reaches higher recognition rate than MLLR, HMM-based model selection and PLT.

scholarly journals The subspace Gaussian mixture model—A structured model for speech recognition

2011 ◽  
Vol 25 (2) ◽  
pp. 404-439 ◽  
Author(s):  
Daniel Povey ◽  
Lukáš Burget ◽  
Mohit Agarwal ◽  
Pinar Akyazi ◽  
Feng Kai ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Structured Model
Sign in / Sign up

Export Citation Format

Share Document