EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models.
Maureen de SeysselAntony D'AvirroAdina WilliamsEmmanuel DupouxPublished in: CoRR (2023)
Keyphrases
- speech recognition
- text to speech
- speech synthesis
- text to speech synthesis
- speech signal
- probabilistic model
- automatic speech recognition
- endpoint detection
- prosodic features
- audio visual
- dialogue system
- spoken language
- computational models
- user interface
- statistical models
- speaker recognition
- facial animation
- statistical model
- process model
- speech recognizer
- spontaneous speech
- acoustic models
- complex systems
- machine learning algorithms
- parameter estimation
- hearing impaired