Linear prediction filtering on cepstral time series for noise-robust speech recognition.
Hsin-Ju HsiehJhih-Hao JhengJung-Shan LinJeih-Weih HungPublished in: ICCE-TW (2016)
Keyphrases
- speech recognition
- speech signal
- linear prediction
- noisy environments
- cepstral coefficients
- background noise
- speech enhancement
- automatic speech recognition
- hidden markov models
- speaker identification
- autoregressive
- language model
- vocal tract
- speaker verification
- image coding
- speech recognizer
- non stationary
- spectral analysis
- pattern recognition
- speech synthesis
- speaker recognition
- lossless compression
- speech recognition systems
- image processing
- prediction error
- image quality
- multiresolution
- image sequences