Employing Linear Prediction Coding in Feature Time Sequences for Robust Speech Recognition in Noisy Environments.
Hao-Teng FanWen-Yu TsengJeih-weih HungPublished in: Int. J. Comput. Linguistics Chin. Lang. Process. (2013)
Keyphrases
- noisy environments
- linear prediction
- speech recognition
- speech signal
- hidden markov models
- cepstral coefficients
- automatic speech recognition
- background noise
- speaker identification
- speech enhancement
- speaker verification
- vocal tract
- digit recognition
- language model
- spectral analysis
- speech synthesis
- voice activity detection
- image coding
- pattern recognition
- word recognition
- image processing
- prediction error
- coding scheme
- noise reduction
- non stationary
- computational complexity
- visual speech
- bayesian networks
- noisy speech
- information retrieval