Independent Component Analysis and Time-Frequency Masking for Speech Recognition in Multitalker Conditions.
Dorothea KolossaRamón Fernandez AstudilloEugen HoffmannReinhold OrglmeisterPublished in: EURASIP J. Audio Speech Music. Process. (2010)
Keyphrases
- speech recognition
- independent component analysis
- signal processing
- independent components
- speech signal
- automatic speech recognition
- factor analysis
- blind source separation
- hidden markov models
- pattern recognition
- speech synthesis
- language model
- principal component analysis
- speech recognition technology
- speech recognition systems
- speaker identification
- noisy environments
- speech recognizer
- machine learning
- single channel
- human visual system
- speaker independent
- principle component analysis
- multi modal
- wavelet transform
- multiresolution
- feature space
- multiscale
- face recognition
- computer vision