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: CoRR (2022)
Keyphrases
- text to speech
- speech signal
- speech recognition
- signal to noise ratio
- speech synthesis
- additive noise
- noisy environments
- modeling method
- speech enhancement
- neural network
- mathematical modeling
- automatic speech recognition
- bio inspired
- background noise
- network architecture
- noise level
- associative memory
- missing data
- acoustic features
- hidden markov models
- pattern recognition