Neural Style Transfer Based Voice Mimicking for Personalized Audio Stories.
Syeda Maryam FatimaMarina ShehzadSyed Sami MurtuzaSyeda Saleha RazaPublished in: AI4TV@MM (2020)
Keyphrases
- emotion recognition
- biologically inspired
- text to speech
- network architecture
- multimedia
- neural network
- voice activity detection
- signal processing
- biologically plausible
- transfer learning
- prosodic features
- knowledge transfer
- audio visual
- user profiles
- visual information
- narrative structure
- e learning
- cross domain
- adaptive learning
- personal experiences
- multi modal
- neural model
- multimedia information
- audio recordings
- associative memory
- audio signals
- audio video
- evolutionary algorithm
- context aware
- interactive storytelling
- speech synthesis
- broadcast news
- music information retrieval
- news stories
- digital video
- learning rules