Aligning Audiovisual Features for Audiovisual Speech Recognition.
Fei TaoCarlos BussoPublished in: ICME (2018)
Keyphrases
- isolated word
- speech recognition
- speech recognition systems
- hidden markov models
- language model
- cepstral coefficients
- speech signal
- pattern recognition
- speech processing
- speech recognition technology
- speech synthesis
- speech recognizer
- noisy environments
- multimedia content
- visual information
- feature vectors
- speaker identification
- audio visual
- video clips
- emotion recognition
- feature set
- speech understanding
- keyword spotting
- speaker independent
- speech retrieval
- speech recognizers
- low level
- multi modal
- information retrieval