Speech discrimination based on multiscale spectro-temporal modulations.
Nima MesgaraniShihab A. ShammaMalcolm SlaneyPublished in: ICASSP (1) (2004)
Keyphrases
- multiscale
- temporal information
- spatio temporal
- speech recognition
- scale space
- spatial and temporal
- temporal databases
- speech signal
- temporal patterns
- image representation
- temporal constraints
- automatic speech recognition
- image segmentation
- temporal data
- coarse to fine
- recognition engine
- temporal evolution
- wavelet transform
- temporal reasoning
- natural images
- space time
- text to speech
- temporal dimension
- emotion recognition
- endpoint detection
- temporal consistency
- audio visual
- image fusion
- wavelet domain
- wavelet coefficients
- subband
- denoising
- hidden markov models