Speech recognition using the atomic speech units constructed from overlapping articulatory features.
Li DengDon X. SunPublished in: EUROSPEECH (1993)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- speech recognition systems
- vocal tract
- speech emotion recognition
- recognition engine
- machine learning
- endpoint detection
- lexical features
- spoken language
- automatic speech recognition
- audio visual
- feature set
- data sets
- feature extraction
- feature vectors
- speech recognizer
- multi stream
- spectral features
- emotion recognition
- hidden markov models
- image features
- dialogue system
- text to speech
- speaker recognition
- speaker verification
- language acquisition
- noisy environments
- speaker identification
- broadcast news
- multi lingual
- low level
- structural features
- prior knowledge
- co occurrence
- feature space
- support vector
- extracted features
- spatial information