Robust Analysis and Weighting on MFCC Components for Speech Recognition and Speaker Identification.
Xi ZhouYun FuMing LiuMark Hasegawa-JohnsonThomas S. HuangPublished in: ICME (2007)
Keyphrases
- speech recognition
- speaker identification
- noisy environments
- speech signal
- speech processing
- hidden markov models
- gaussian mixture model
- speaker recognition
- language model
- speaker dependent
- pattern recognition
- speaker independent
- language identification
- probabilistic neural network
- automatic speech recognition
- speaker diarization
- mel frequency cepstral coefficients
- speech recognition systems
- neural network
- broadcast news
- speech recognizer
- feature space
- feature extraction
- machine learning
- speaker verification
- computer vision