Linear Prediction-based Parallel WaveGAN Speech Synthesis.
Min-Jae HwangHyun-Wook YoonChan-Ho SongJin-Seob KimJae-Min KimEunwoo SongPublished in: ICEIC (2022)
Keyphrases
- speech synthesis
- linear prediction
- vocal tract
- speech recognition
- speech signal
- image coding
- text to speech
- lossless compression
- hidden markov models
- prediction error
- prosodic features
- automatic speech recognition
- autoregressive
- neural network
- subband
- noisy environments
- filter bank
- language model
- image data
- computational complexity
- information retrieval