GAN-based Augmentation for Populating Speech Dataset with High Fidelity Synthesized Audio.
Moon-Ki BackSeung Won YoonKyu-Chul LeePublished in: ICTC (2020)
Keyphrases
- high fidelity
- audio visual
- audio stream
- text to speech
- emotion recognition
- real time
- audio signals
- broadcast news
- multi modal
- high quality
- medical image compression
- speech recognition
- speaker identification
- multimedia
- digital audio
- audio features
- cepstral features
- speech synthesis
- audio recordings
- prosodic features
- automatic transcription
- spoken documents
- audio signal
- automatic speech recognition
- speech signal
- visual information
- speech music discrimination
- linear predictive coding
- high resolution
- intelligent systems
- multi stream
- acoustic features
- human operators