Evaluating Speech-Phoneme Alignment and its Impact on Neural Text-To-Speech Synthesis.
Frank ZalkowPrachi GovalkarMeinard MüllerEmanuël A. P. HabetsChristian DittmarPublished in: ICASSP (2023)
Keyphrases
- text to speech synthesis
- text to speech
- speech synthesis
- speech recognition
- prosodic features
- network architecture
- image alignment
- automatic speech recognition
- automatic speech recognition systems
- speech signal
- neural network
- hidden markov models
- neural fuzzy
- bio inspired
- dynamic time warping
- visual speech
- genetic algorithm
- data sets