Segmentation of speech for speaker and language recognition.
André Gustavo AdamiHynek HermanskyPublished in: INTERSPEECH (2003)
Keyphrases
- speech recognition
- automatic speech recognition systems
- recognition engine
- speaker dependent
- automatic speech recognition
- automatic transcription
- speaker independent
- speech sounds
- audio visual
- speaker verification
- phoneme recognition
- speaker recognition
- speaker identification
- hidden markov models
- segmentation algorithm
- image parsing
- language acquisition
- text to speech
- speech corpus
- visual speech recognition
- spoken words
- segmentation method
- noisy environments
- spoken language
- image segmentation
- medical images
- programming language
- symbol recognition
- visual speech
- numeral strings
- correct recognition
- object recognition
- natural language
- feature extraction
- recognition rate
- multiscale
- text to speech synthesis
- speech signal
- recognition algorithm
- speech recognition systems
- prosodic features
- noisy speech
- level set
- speech synthesis
- broadcast news
- word recognition
- word segmentation
- speaker diarization
- speaker adaptation
- english text
- handwriting recognition
- dialogue system
- language learning
- mel frequency cepstral coefficients
- vocal tract
- speech segments
- recognition process