Graphspeech: Syntax-aware Graph Attention Network For Neural Speech Synthesis

Abstract

Attention-based end-to-end text-to-speech synthesis (TTS) is superior to conventional statistical methods in many ways. Transformer-based TTS is one of such successful implementations. While Transformer TTS models the speech frame sequence well with a self-attention mechanism, it does not associate input text with output utterances from a syntactic point of view at sentence level. We propose a novel neural TTS model, denoted as GraphSpeech, that is formulated under graph neural network framework. GraphSpeech encodes explicitly the syntactic relation of input lexical tokens in a sentence, and incorporates such information to derive syntactically motivated character embeddings for TTS attention mechanism. Experiments show that GraphSpeech consistently outperforms the Transformer TTS baseline in terms of spectrum and prosody rendering of utterances.

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keyliu2020graphspeech

Related papers

• Neural Speech Synthesis With Transformer Network (2018)19.95
• Hignn-tts: Hierarchical Prosody Modeling With Graph Neural Networks For Expressive Long-form TTS (2023)5.84
• Fastspeech: Fast, Robust And Controllable Text To Speech (2019)0.00
• Transformer Based Grapheme-to-phoneme Conversion (2020)11.39
• T-GSA: Transformer With Gaussian-weighted Self-attention For Speech Enhancement (2019)15.95
• Feathertts: Robust And Efficient Attention Based Neural TTS (2020)5.84
• Generating Synthetic Audio Data For Attention-based Speech Recognition Systems (2019)12.68
• Enhancing Speaking Styles In Conversational Text-to-speech Synthesis With Graph-based Multi-modal Context Modeling (2021)0.00