GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-Spectrogram.
Lauri JuvelaBajibabu BollepalliJunichi YamagishiPaavo AlkuPublished in: INTERSPEECH (2019)
Keyphrases
- speech synthesis
- linear prediction
- speech signal
- speech recognition
- cepstral coefficients
- automatic speech recognition
- vocal tract
- structuring elements
- noisy environments
- hidden markov models
- speaker identification
- pattern recognition
- prosodic features
- language model
- spectral analysis
- acoustic features
- neural network
- data structure