Multi-Encoder Sequential Attention Network for Context-Aware Speech Recognition in Japanese Dialog Conversation.
Nobuya TachimoriSakriani SaktiSatoshi NakamuraPublished in: O-COCOSDA (2021)
Keyphrases
- context aware
- speech recognition
- dialog systems
- contextual information
- hidden markov models
- mobile devices
- ambient intelligence
- ubiquitous computing
- context awareness
- language model
- speech synthesis
- speech signal
- ubiquitous learning
- speech recognition systems
- automatic speech recognition
- pattern recognition
- speech recognition technology
- speech processing
- smart spaces
- natural language
- smart environments
- noisy environments
- speaker independent
- mobile users
- context aware services
- speech recognizer
- bit rate
- current context
- smart home
- conversational agents
- context aware systems
- computer vision
- context aware ubiquitous learning
- speaker identification
- language modeling
- metadata