Lipper: Speaker Independent Speech Synthesis Using Multi-View Lipreading.
Khwaja Mohd. SalikSwati AggarwalYaman KumarRajiv Ratn ShahRohit JainRoger ZimmermannPublished in: AAAI (2019)
Keyphrases
- multi view
- speech synthesis
- speech recognition
- speaker independent
- single view
- multiple views
- hidden markov models
- speech recognizer
- language model
- vocal tract
- automatic speech recognition
- d objects
- depth map
- speech signal
- pattern recognition
- three dimensional
- multi view images
- speech recognition systems
- speaker identification
- semi supervised
- multi view clustering
- co training
- noisy environments
- viewpoint
- neural network
- multi view learning
- visual information
- digit recognition
- unsupervised learning
- data mining