Multimodal Machine Learning: Integrating Language, Vision and Speech.
Louis-Philippe MorencyTadas BaltrusaitisPublished in: ACL (Tutorial Abstracts) (2017)
Keyphrases
- machine learning
- multimodal interfaces
- audio visual
- computer vision
- language acquisition
- text to speech
- english text
- text to speech synthesis
- speech processing
- multi modal
- natural language
- speech recognition
- multimodal interaction
- spoken language
- multi stream
- data mining
- language learning
- machine learning algorithms
- knowledge acquisition
- vision system
- real time
- pattern recognition
- programming language
- human language
- machine learning methods
- learning algorithm
- computational linguistics
- image processing
- feature selection
- spoken dialog systems
- speech signal
- active learning
- human computer interaction
- decision trees
- human communication
- automatic speech recognition
- recognition engine
- language generation
- knowledge representation
- learning tasks
- computational intelligence
- speech synthesis
- knowledge discovery
- multimedia
- reinforcement learning
- supervised learning
- specification language
- noisy environments
- multi party
- explanation based learning
- machine learning approaches
- hidden markov models
- inductive learning