Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Dependency ParsingRepresentation LearningSentenceSpeech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Joint Unsupervised Learning of Semantic Representation of Words and Roles in Dependency Trees
In this paper, we introduce WoRel, a model that jointly learns word embeddings and a semantic representation of word relations. The model learns from plain text sentences and their dependency parse trees. The word embedd…
Named Entity Recognition (NER)Question AnsweringSentenceSentiment Analysis+2Cross-Lingual Syntactically Informed Distributed Word Representations
We develop a novel cross-lingual word representation model which injects syntactic information through dependency-based contexts into a shared cross-lingual word vector space. The model, termed CL-DepEmb, is based on the…
Bilingual Lexicon InductionEntity LinkingInformation RetrievalSemantic Similarity+7Compositional Sentence Representation from Character within Large Context Text
This paper describes a Hierarchical Composition Recurrent Network (HCRN) consisting of a 3-level hierarchy of compositional models: character, word and sentence. This model is designed to overcome two problems of represe…
Dialogue Act ClassificationGeneral ClassificationSentenceIncorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing…
Learning Word EmbeddingsRepresentation LearningWord EmbeddingsDependency-based Hybrid Trees for Semantic Parsing
We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the seman…
Semantic Parsing