Extracting singing voice from music recordings by cascading audio decomposition techniques.
Jonathan DriedgerMeinard MüllerPublished in: ICASSP (2015)
Keyphrases
- music information retrieval
- audio recordings
- audio features
- acoustic features
- audio visual
- mel frequency cepstral coefficients
- music genre classification
- emotion recognition
- music retrieval
- music collections
- audio signal
- digital music
- music recommendation
- genre classification
- speaker verification
- information retrieval systems
- low level
- decomposition method
- decomposition algorithm
- music score
- audio signals
- visual features
- audio content
- audio stream
- music scores
- automatic music genre classification
- multi modal
- digital audio
- feature set
- multimedia
- sound source
- text data
- polyphonic music
- prosodic features
- image classification
- hidden markov models
- metadata