A VQ-Based Single-Channel Audio Separation for Music/Speech Mixtures.
Meysam AsgariMahdi FallahElahe Abouie MehriziAli MostafaviPublished in: UKSim (2009)
Keyphrases
- audio features
- sound source
- single channel
- source separation
- speech signal
- audio visual
- speech enhancement
- acoustic features
- audio signal
- image coding
- speaker identification
- speech recognition
- audio signals
- low level
- image compression
- focus of attention
- music information retrieval
- multi modal
- real environment
- visual features
- linear prediction
- vocal tract
- blind source separation
- multimedia
- automatic speech recognition
- visual data
- image quality
- hidden markov models
- multiscale