Isolated spoken word recognition using packed-MFCC on padded-voice signal for unscripted languages.
Rajdev TiwariVidha SharmaRamesh Chandra SahooPublished in: Int. J. Comput. Vis. Robotics (2022)
Keyphrases
- expressive power
- fundamental frequency
- signal processing
- speech signal
- frequency domain
- feature extraction
- language independent
- speech quality
- high frequency
- non stationary
- databases
- speech recognition
- cross lingual
- language identification
- denoising
- text summarization
- measured data
- mel frequency cepstral coefficients
- query language
- feature vectors
- impulse response
- face recognition