On incorporating social speaker characteristics in synthetic speech.
Sai Sirisha RallabandiSebastian MöllerPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- speaker verification
- automatic speech recognition
- speaker identification
- social media
- speech signal
- automatic speech recognition systems
- social networks
- social interaction
- real images are presented
- vocal tract
- multimedia
- speech synthesis
- acoustic features
- prosodic features
- speaker diarization
- pattern recognition
- gaussian mixture model
- social networking
- text to speech
- speech recognizer
- multi modal
- broadcast news
- acoustic models
- vector quantization
- speech sounds