Can We Generate Emotional Pronunciations for Expressive Speech Synthesis?
Marie TahonGwénolé LecorvéDamien LolivePublished in: IEEE Trans. Affect. Comput. (2020)
Keyphrases
- speech synthesis
- speech recognition
- vocal tract
- text to speech
- prosodic features
- hidden markov models
- speech recognition systems
- automatic speech recognition
- pattern recognition
- speech signal
- language model
- automatically generating
- automatically generate
- speech recognizer
- data mining
- computer vision
- artificial intelligence