Discrimination of speech from nonspeech based on multiscale spectro-temporal Modulations.
Nima MesgaraniMalcolm SlaneyShihab A. ShammaPublished in: IEEE Trans. Speech Audio Process. (2006)
Keyphrases
- multiscale
- speech recognition
- spatio temporal
- spatial and temporal
- temporal data
- temporal constraints
- computer vision
- edge detection
- space time
- image processing
- temporal information
- scale space
- temporal reasoning
- temporal consistency
- recognition engine
- feature selection
- image fusion
- text to speech
- speech synthesis
- multiscale analysis
- temporal relations
- temporal patterns
- shape representation
- image representation
- image registration
- image segmentation
- affine invariant
- automatic speech recognition
- dialogue system
- temporal evolution
- wavelet transform
- feature extraction
- audio stream