Speech enhancement using a modified Kalman filter based on complex linear prediction and supergaussian priors.
Thomas EschPeter VaryPublished in: ICASSP (2008)
Keyphrases
- linear prediction
- speech enhancement
- image coding
- speech signal
- noise reduction
- lossless compression
- vocal tract
- prediction error
- subband
- single channel
- autoregressive
- information retrieval
- noisy environments
- speech recognition
- filter bank
- signal to noise ratio
- multi channel
- spectral analysis
- high frequency
- image compression
- motion estimation
- probabilistic model