Effects of Speech Duration on Preserving the Identity of Synthesized Voice.
Papapin SupmeeKlittiya SuwanmalaiNatkrita HanchoenkulNapa Sae-BaeBanphatee KhomkhamPublished in: JCSSE (2023)
Keyphrases
- text to speech
- emotion recognition
- speech recognition errors
- speech synthesis
- voice activity detection
- speech recognition
- speech quality
- data sets
- fundamental frequency
- audio visual
- neural network
- speech sounds
- database
- speech signal
- automatic speech recognition
- noisy environments
- pattern recognition
- spoken language
- image details
- feature extraction