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.

arXiv commentTo appear at ICASSP'2021 (Accepted). (Speech samples: https://ttslr.github.io/GraphSpeech/)

References in corpus (4)

• Hierarchical Generative Modeling for Controllable Speech Synthesis
• Modeling Prosodic Phrasing with Multi-Task Learning in Tacotron-based TTS
• Expressive TTS Training with Frame and Style Reconstruction Loss
• Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset

Cited by in corpus (2)

• A Survey on Neural Speech Synthesis
• Review of end-to-end speech synthesis technology based on deep learning