A new nonlinear prediction model based on the Recurrent Neural Predictive Hidden Markov Model for speech enhancement.
Joohim LeeChangwoo SeoKi Yong LeePublished in: ICASSP (2002)
Keyphrases
- hidden markov models
- speech enhancement
- noisy speech
- speech signal
- linear prediction
- speech recognition
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- automatic speech recognition
- background noise
- image coding
- prediction error
- vocal tract
- conditional random fields
- wiener filter
- speaker identification
- graphical models
- non stationary
- independent component analysis
- information retrieval