Introducing Speaker Vectors for Child Speech Synthesis in Neural Vocoders.
Satoshi YoshidaKen'ichi FuruyaHideyuki MizunoPublished in: CISIS (2022)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- network architecture
- neural network
- automatic speech recognition
- speaker dependent
- hidden markov models
- pattern recognition
- speech signal
- speech corpus
- speaker identification
- language model
- neural computation
- vector space
- noisy environments
- neural model
- neural fuzzy
- feature vectors
- audio visual
- machine learning
- speaker adaptation
- family members
- principal components
- word processing
- speaker recognition
- image processing
- multi modal
- bio inspired
- feature selection
- associative memory
- information retrieval
- image acquisition