Co-Speech Gesture Generation via Audio and Text Feature Engineering.
Geunmo KimJaewoong YooHyedong JungPublished in: ICMI Companion (2023)
Keyphrases
- feature engineering
- speech processing
- text to speech
- english text
- audio stream
- speech recognition
- signal processing
- audio visual
- spoken documents
- dependency parsing
- speaker identification
- text classification
- multi stream
- broadcast news
- natural language processing
- machine learning
- multimodal interfaces
- hidden markov models
- text data
- information retrieval
- spontaneous speech
- text mining
- audio features
- multimedia
- speech signal
- artificial intelligence
- gesture recognition
- video search
- multimedia systems
- multimodal interaction
- multimedia information
- knowledge base
- variable length
- human computer interaction
- feature set
- music information retrieval
- domain knowledge
- feature selection
- automatic speech recognition