DEEPA: A Deep Neural Analyzer for Speech and Singing Vocoding.
Sergey NikonorovBerrak SismanMingyang ZhangHaizhou LiPublished in: ASRU (2021)
Keyphrases
- audio features
- network architecture
- speech recognition
- acoustic features
- text to speech
- speech synthesis
- neural network
- speech signal
- nonlinear predictive control
- bio inspired
- audio visual
- recognition engine
- spoken language
- automatic speech recognition
- language acquisition
- emotion recognition
- neural model
- artificial neural
- neural computation
- data acquisition
- multi modal
- spiking neural networks
- speech processing
- deep learning
- english text
- speaker recognition
- biologically plausible
- music information retrieval
- biologically inspired
- associative memory
- information retrieval