Back to Search
Start Over
Using Linear Interpolation to Improve Histogram Equalization for Speech Recognition
- Source :
- 8th International Conference on Spoken Language Processing-ICSLP'2004, 8th International Conference on Spoken Language Processing-ICSLP'2004, 2004, Jeju, Corée du Sud, 4 p, INTERSPEECH
- Publication Year :
- 2004
- Publisher :
- HAL CCSD, 2004.
-
Abstract
- Colloque avec actes et comité de lecture. internationale.; International audience; This paper presents a novel approach to speech data normalization by introducing interpolation for histogram equalization. We study different ways of histogram interpolation that inhence this normalization technique. We found that using a special weighting factor to combine current and past test sentence statistics improved speech recognition performance.
- Subjects :
- Normalization (statistics)
Computer science
Color normalization
Speech recognition
[INFO.INFO-OH]Computer Science [cs]/Other [cs.OH]
Normalization (image processing)
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Linear interpolation
030507 speech-language pathology & audiology
03 medical and health sciences
Histogram
0202 electrical engineering, electronic engineering, information engineering
histogram equalization for speech recogntion
Histogram equalization
égalisation d'histogramme pour la reconnaissance de la parole
business.industry
Histogram matching
020206 networking & telecommunications
Pattern recognition
Weighting
Adaptive histogram equalization
Artificial intelligence
0305 other medical science
business
Interpolation
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- 8th International Conference on Spoken Language Processing-ICSLP'2004, 8th International Conference on Spoken Language Processing-ICSLP'2004, 2004, Jeju, Corée du Sud, 4 p, INTERSPEECH
- Accession number :
- edsair.doi.dedup.....2f2ca0504b459e41534b4cb16dccf990