AVATAR: Unconstrained Audiovisual Speech Recognition.
Valentin GabeurPaul Hongsuck SeoArsha NagraniChen SunKarteek AlahariCordelia SchmidPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- hidden markov models
- speech synthesis
- speech processing
- automatic speech recognition
- speech signal
- language model
- pattern recognition
- speech recognition technology
- speech recognizer
- handwriting recognition
- video retrieval
- speech understanding
- speaker identification
- multimedia content
- keyword spotting
- maximum likelihood
- audio visual
- speech recognition errors
- speech recognition systems
- visual information
- noisy environments
- cepstral coefficients
- speech retrieval
- multi modal
- background noise
- emotion recognition