Virtual Acoustic Channel Expansion Based on Neural Networks for Weighted Prediction Error-Based Speech Dereverberation.
Joon-Young YangJoon-Hyuk ChangPublished in: INTERSPEECH (2020)
Keyphrases
- prediction error
- neural network
- reversible watermarking
- linear prediction
- motion compensated
- speech recognition
- speech sounds
- acoustic features
- speech recognition systems
- emotional speech
- prosodic features
- inter frame
- motion vectors
- vocal tract
- speech signal
- speech synthesis
- multi channel
- speaker independent
- audio visual
- formant frequencies
- automatic speech recognition
- power spectral density
- bit rate
- linear predictors
- vowel phonemes
- text to speech
- speaker verification
- broadcast news
- block matching
- back propagation
- motion estimation
- multimedia