Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis

Conference of the International Speech Communication Association (INTERSPEECH)(2022)

引用 1|浏览5
暂无评分
摘要
Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to embody semantic information and employed to TTS recently. However, original or simply fine-tuned BERT embeddings still cannot provide sufficient semantic knowledge that expressive TTS models should take into account. In this paper, we propose a word-level semantic representation enhancing method based on dependency structure and pre-trained BERT embedding. The BERT embedding of each word is reprocessed considering its specific dependencies and related words in the sentence, to generate more effective semantic representation for TTS. To better utilize the dependency structure, relational gated graph network (RGGN) is introduced to make semantic information flow and aggregate through the dependency structure. The experimental results show that the proposed method can further improve the naturalness and expressiveness of synthesized speeches on both Mandarin and English datasets.
更多
查看译文
关键词
synthesis,dependency structure,word-level,text-to-speech
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要