Infants temporally coordinate gesture-speech combinations before they produce their first words.
Núria Esteve-GibertPilar PrietoPublished in: Speech Commun. (2014)
Keyphrases
- multimodal interfaces
- language acquisition
- hand movements
- text recognition
- continuous speech recognition
- grapheme to phoneme conversion
- speech recognition
- speech recognition systems
- gesture recognition
- recognition errors
- spontaneous speech
- spoken document retrieval
- speech recognition errors
- n gram
- spoken words
- speech corpus
- word sense disambiguation
- hidden markov models
- lexical features
- automatic transcription
- conversational speech
- temporal information
- multi stream
- spatio temporal
- keywords
- natural language
- speech sounds
- english words
- audio visual
- human computer interaction
- english text
- related words
- human machine interaction
- continuous stream
- spoken language
- word segmentation
- noisy environments
- automatic speech recognition
- hand gestures
- natural language processing