Generative Adversarial Training For Text-to-speech Synthesis Based On Raw Phonetic Input And Explicit Prosody Modelling

Abstract

We describe an end-to-end speech synthesis system that uses generative adversarial training. We train our Vocoder for raw phoneme-to-audio conversion, using explicit phonetic, pitch and duration modeling. We experiment with several pre-trained models for contextualized and decontextualized word embeddings and we introduce a new method for highly expressive character voice matching, based on discreet style tokens.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyboros2023generative

Related papers

• End-to-end Adversarial Text-to-speech (2020)0.00
• End-to-end Video-to-speech Synthesis Using Generative Adversarial Networks (2021)11.58
• Expediting TTS Synthesis With Adversarial Vocoding (2019)6.77
• Conditional Variational Autoencoder With Adversarial Learning For End-to-end Text-to-speech (2021)0.00
• Generative Adversarial Network-based Glottal Waveform Model For Statistical Parametric Speech Synthesis (2019)10.35
• Adversarial Learning Of Intermediate Acoustic Feature For End-to-end Lightweight Text-to-speech (2022)0.00
• Delightfultts 2: End-to-end Speech Synthesis With Adversarial Vector-quantized Auto-encoders (2022)9.23
• High Fidelity Speech Synthesis With Adversarial Networks (2019)0.00