Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise.
Tuomo RaitioPetko PetkovJiangchuan LiP. V. Muhammed ShifasAndrea DavisYannis StylianouPublished in: INTERSPEECH (2022)
Keyphrases
- text to speech
- speech signal
- speech recognition
- signal to noise ratio
- noisy environments
- speech synthesis
- additive noise
- neural network
- emotion recognition
- speech enhancement
- automatic speech recognition
- bio inspired
- modeling method
- noisy data
- random noise
- mathematical modeling
- prosodic features
- multi modal
- real images are presented
- speech quality
- audio visual
- intelligent tutoring systems
- real world