Local Feature or Mel Frequency Cepstral Coefficients - Which One is Better for MLN-Based Bangla Speech Recognition?
Foyzul HassanMohammed Rokibul Alam KotwalMd. Mostafizur RahmanMohammad NasiruddinMd. Abdul LatifMohammad Nurul HudaPublished in: CoRR (2013)
Keyphrases
- speech recognition
- cepstral coefficients
- mel frequency cepstral coefficients
- speaker identification
- speech signal
- hidden markov models
- speaker recognition
- speech recognition systems
- pattern recognition
- automatic speech recognition
- language model
- speech recognizer
- noisy environments
- feature vectors
- feature set
- acoustic features
- linear prediction
- multi modal
- gaussian mixture model
- probabilistic neural network
- probabilistic model
- speaker diarization
- low level
- machine learning