Neural Synthesis of Binaural Speech From Mono Audio.
Alexander RichardDejan MarkovicIsrael D. GebruSteven KrennGladstone Alexander ButlerFernando De la TorreYaser SheikhPublished in: ICLR (2021)
Keyphrases
- audio stream
- audio visual
- broadcast news
- audio signals
- audio features
- cepstral features
- text to speech
- speaker identification
- sound source
- digital audio
- emotion recognition
- audio recordings
- speech music discrimination
- prosodic features
- speech recognition
- network architecture
- speech processing
- acoustic signals
- multi stream
- neural network
- automatic transcription
- program synthesis
- multimedia
- acoustic features
- spoken documents
- speech synthesis
- audio video
- facial animation
- visual information
- multi modal
- speaker verification
- linear predictive coding
- voice activity detection
- neural model
- noisy environments
- digital video
- speech signal
- human language
- visual data
- automatic speech recognition
- bio inspired
- hidden markov models
- texture synthesis
- visual speech
- audio signal
- human computer interaction
- feature extraction
- image enhancement
- video streams
- soccer video
- music information retrieval
- learning rules
- transfer function