Non-Intrusive Binaural Speech Intelligibility Prediction From Discrete Latent Representations.
Alex F. McKinneyBenjamin CauchiPublished in: IEEE Signal Process. Lett. (2022)
Keyphrases
- speech recognition
- sequence prediction
- linear prediction
- prediction accuracy
- prediction algorithm
- grey prediction model
- speech synthesis
- prediction error
- signal to noise ratio
- prediction model
- speech signal
- audio visual
- pattern recognition
- latent variables
- speaker identification
- video sequences
- discrete version
- recognition engine
- high dimensional
- discrete geometry
- text to speech
- multiple representations
- spoken language
- recommender systems
- human computer interaction
- symbolic representation
- random variables
- feature extraction
- finite number
- visual information