Results on perceptual invariants to transformations on speech.
Arnaud RobertPublished in: ICASSP (1999)
Keyphrases
- quasi invariant
- speech recognition
- perceptual grouping
- automatic speech recognition
- text to speech
- human visual system
- spoken language
- recognition engine
- speech signal
- invariant features
- endpoint detection
- speech synthesis
- language acquisition
- invariant representations
- moment invariants
- low level
- perceptual organization
- human perception
- affine invariant
- broadcast news
- projective invariants
- audio stream
- affine moment invariants
- human vision
- speaker identification
- linear prediction
- high level
- visual perception
- audio visual
- natural images
- natural language