Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition.
Abhinav ThandaShankar M. VenkatesanPublished in: CoRR (2017)
Keyphrases
- audio visual
- multi task learning
- automatic speech recognition
- neural network
- speech recognition
- multi task
- multi modal
- gaussian processes
- learning tasks
- speech signal
- visual information
- hidden markov models
- pattern recognition
- learning problems
- broadcast news
- visual data
- multimedia
- transfer learning
- noisy environments
- acoustic features
- audio features
- learning algorithm
- passage retrieval
- language model
- machine learning