Towards Phoneme Landmarks Identification for American-English using a Multimodal Speech Capture System.
Nordine SebkhiYana YunusovaMaysam GhovanlooPublished in: BioCAS (2018)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- automatic speech recognition
- automatic speech recognition systems
- multimodal interaction
- broadcast news
- speech recognition technology
- english text
- audio visual
- speech signal
- phoneme recognition
- speaker dependent
- prosodic features
- visual speech
- spoken language
- multimodal interfaces
- united states
- vocal tract
- multi modal
- hidden markov models
- english language
- language model
- multi stream
- context dependent
- speech recognizer
- multimedia
- language learning
- cross lingual
- speaker adaptation
- speech recognition systems
- information retrieval
- pattern recognition
- noisy environments
- natural language
- word processing
- speaker identification