RWEN-TTS: Relation-Aware Word Encoding Network for Natural Text-to-Speech Synthesis


  • Shinhyeok Oh Netmarble AI Center
  • HyeongRae Noh Netmarble AI Center
  • Yoonseok Hong Netmarble AI Center
  • Insoo Oh Netmarble AI Center



SNLP: Speech and Multimodality, SNLP: Generation, SNLP: Language Models, SNLP: Sentence-Level Semantics and Textual Inference, SNLP: Syntax -- Tagging, Chunking & Parsing


With the advent of deep learning, a huge number of text-to-speech (TTS) models which produce human-like speech have emerged. Recently, by introducing syntactic and semantic information w.r.t the input text, various approaches have been proposed to enrich the naturalness and expressiveness of TTS models. Although these strategies showed impressive results, they still have some limitations in utilizing language information. First, most approaches only use graph networks to utilize syntactic and semantic information without considering linguistic features. Second, most previous works do not explicitly consider adjacent words when encoding syntactic and semantic information, even though it is obvious that adjacent words are usually meaningful when encoding the current word. To address these issues, we propose Relation-aware Word Encoding Network (RWEN), which effectively allows syntactic and semantic information based on two modules (i.e., Semantic-level Relation Encoding and Adjacent Word Relation Encoding). Experimental results show substantial improvements compared to previous works.




How to Cite

Oh, S., Noh, H., Hong, Y., & Oh, I. (2023). RWEN-TTS: Relation-Aware Word Encoding Network for Natural Text-to-Speech Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 13428-13436.



AAAI Technical Track on Speech & Natural Language Processing