Pitch estimation of speech and music sound based on multi-scale product with auditory feature extraction.
Mohamed Anouar Ben MessaoudAïcha BouzidPublished in: Int. J. Speech Technol. (2016)
Keyphrases
- acoustic features
- feature extraction
- multiscale
- environmental sounds
- musical instrument
- audio features
- sound source
- musical instruments
- mel frequency cepstral coefficients
- speech signal
- music information retrieval
- wavelet transform
- audio signals
- speaker identification
- automatic speech recognition
- visual features
- audio signal
- fundamental frequency
- linear predictive
- speaker verification
- image processing
- speech recognition
- keypoint detection
- image classification
- automatic speech recognition systems
- speech music discrimination
- visual speech
- dimensionality reduction
- life cycle
- edge detection
- frequency domain
- preprocessing
- local binary pattern
- feature space
- feature vectors
- audio content
- feature selection
- speech synthesis
- music retrieval
- signal processing
- natural images
- image representation
- optical flow estimation
- visual information
- audio visual
- texture analysis
- feature set
- multiresolution
- product information
- digital audio
- information processing
- optic flow
- pattern classification