DeePMOS: Deep Posterior Mean-Opinion-Score of Speech.
Xinyu LiangFredrik CumlinChristian SchüldtSaikat ChatterjeePublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- correlation coefficient
- bayesian framework
- probability distribution
- endpoint detection
- probabilistic model
- speech synthesis
- gaussian process
- speech signal
- text to speech
- recognition engine
- posterior probability
- audio visual
- spoken language
- automatic speech recognition systems
- broadcast news
- data sets
- image quality assessment
- noisy environments
- structural similarity
- posterior distribution
- human computer interaction
- audio stream
- feature vectors
- text to speech synthesis
- pattern recognition