TTS voice corpus reduction for audio-book generation.
Meysam ShamsiPublished in: JEP-TALN-RECITAL (3) (2020)
Keyphrases
- text to speech
- word processing
- prosodic features
- speech synthesis
- book presents
- spontaneous speech
- book covers
- multimodal interaction
- cutting edge
- generation process
- emotion recognition
- graduate students
- speaker verification
- manually annotated
- multimedia
- audio signals
- voice activity detection
- topics covered include
- data mining
- multimedia information
- text data
- researchers and practitioners
- test set
- computer science
- information retrieval