Second- and third-order wigner distributions in hierarchical recognition of speech phonemes.
Maria RangoussiFlemming PedersenPublished in: EUROSPEECH (1995)
Keyphrases
- speech recognition
- phoneme recognition
- speech signal
- speech recognition systems
- recognition engine
- speech synthesis
- automatic speech recognition systems
- hidden markov models
- speech corpus
- automatic speech recognition
- speaker independent
- recognition rate
- speaker dependent
- recognition accuracy
- text to speech
- pattern recognition
- noisy environments
- object recognition
- automatic recognition
- handwriting recognition
- probability distribution
- random variables
- character recognition
- computer vision
- speaker identification
- speech recognizer
- text recognition
- recognition of partially occluded
- speech sounds
- unsupervised learning
- sign language
- spoken language
- word recognition
- vocal tract
- hierarchical structure
- action recognition
- audio signal
- natural language processing
- automatic transcription
- recognition process
- gait recognition