A Mel Spectrogram Enhancement Paradigm Based on CWT in Speech Synthesis.
Guoqiang HuHuaning TanRuilai LiPublished in: CoRR (2024)
Keyphrases
- speech synthesis
- speech recognition
- speech signal
- text to speech
- cepstral coefficients
- vocal tract
- automatic speech recognition
- prosodic features
- image enhancement
- pattern analysis
- language model
- image processing
- neural network
- data sets
- wavelet transform
- wavelet transformation
- single channel
- computer vision
- information retrieval