Speech signals protection via logo watermarking based on the time-frequency analysis.
Irena OrovicPredrag ZogovicNikola ZaricSrdjan StankovicPublished in: Ann. des Télécommunications (2008)
Keyphrases
- speech signal
- non stationary
- speech recognition
- vocal tract
- automatic speech recognition
- spectral analysis
- background noise
- additive noise
- automatic speech recognition systems
- linear prediction
- watermarking scheme
- noisy environments
- copyright protection
- blind source separation
- speaker identification
- hidden markov models
- speech enhancement
- watermarking technique
- digital watermarking
- multiresolution
- fundamental frequency
- neural network
- speech quality
- speech sounds
- pattern recognition
- language model
- watermarking algorithm
- probabilistic model
- multi channel
- noisy images