SBVQA 2.0: Robust End-to-End Speech-Based Visual Question Answering for Open-Ended Questions.
Faris AlasmarySaad Al-AhmadiPublished in: IEEE Access (2023)
Keyphrases
- end to end
- question answering
- information retrieval
- information extraction
- question classification
- passage retrieval
- natural language
- natural language processing
- open ended questions
- text localization and recognition
- speech transcripts
- congestion control
- named entities
- qa clef
- cross language
- open domain question answering
- speech recognition
- syntactic information
- sentence retrieval
- visual information
- question answering systems
- speech signal
- audio visual
- qa systems
- candidate answers
- answering questions