Seeing wake words: Audio-visual Keyword Spotting.
Liliane MomeniTriantafyllos AfourasThemos StafylakisSamuel AlbanieAndrew ZissermanPublished in: CoRR (2020)
Keyphrases
- audio visual
- keyword spotting
- printed documents
- multi modal
- speech recognition
- hidden markov models
- visual information
- handwritten documents
- speech processing
- n gram
- character recognition
- multi stream
- multimedia
- visual data
- document images
- artificial intelligence
- document analysis
- word recognition
- language independent
- image database
- co occurrence
- data analysis