ParalMGC: Multiple Audio Representations for Synthetic Human Speech Attribution.
Michael NeriAnna FerrarottiLuca De LuisaAndrea SalimbeniMarco CarliPublished in: EUVIP (2022)
Keyphrases
- audio visual
- audio stream
- speech recognition
- broadcast news
- human language
- language acquisition
- multimedia
- real world
- cepstral features
- digital audio
- signal processing
- speaker identification
- audio video
- hand movements
- visual data
- audio signals
- human communication
- multi stream
- speech synthesis
- speaker diarization
- human subjects
- visual information
- visual features