Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition.
Chanwoo KimRichard M. SternPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
- speech recognition
- cepstral coefficients
- speaker diarization
- noisy environments
- speech signal
- hidden markov models
- automatic speech recognition
- language model
- feature set
- pattern recognition
- speaker identification
- audio signal
- speaker verification
- machine learning
- linear prediction
- mel frequency cepstral coefficients
- multi modal
- image processing
- computer vision