Back to Search
Start Over
Study of speech features robustness for speaker verification application in noisy environments
- Source :
- IST
- Publication Year :
- 2016
- Publisher :
- IEEE, 2016.
-
Abstract
- This paper presents a comparative study and evaluation of the performances of four speech feature vectors, i.e., MFCC, IMFCC, LFCC, and PNCC in a speaker verification system based on speaker modeling through the Gaussian mixture model (GMM) under clean and noisy speech conditions. The TIMIT and NOISEX92 dataset were used in implementing the tests for speech signal and noise, respectively. The evaluation results show that IMFCC and PNCC provide superior performance in the presence of noise. In order to enhance the performance of the system under noisy conditions, the application of spectral subtraction algorithm as a pre-processing stage was investigated. It only improved the performance for the speech signal contaminated with white noise.
- Subjects :
- Noise measurement
Computer science
business.industry
Speech recognition
Feature vector
020206 networking & telecommunications
Pattern recognition
TIMIT
02 engineering and technology
White noise
Mixture model
01 natural sciences
Robustness (computer science)
0103 physical sciences
0202 electrical engineering, electronic engineering, information engineering
Mel-frequency cepstrum
Artificial intelligence
Hidden Markov model
business
010301 acoustics
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2016 8th International Symposium on Telecommunications (IST)
- Accession number :
- edsair.doi...........a7ce5033ef455c6d573d6152ef65f1e6