paper-with-me

Papers

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

2021-04-14 · Yixuan Zhou, Changhe Song, Jingbei Li, Zhiyong Wu, Yanyao Bian, Dan Su, Helen Meng

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.

📄 PDF Abstract BibTeX arXiv:2104.06835

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency ParsingRepresentation LearningSentenceSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Joint Unsupervised Learning of Semantic Representation of Words and Roles in Dependency Trees

2017-09-01 · RANLP 2017 9 · Michal Konkol

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+2

Cross-Lingual Syntactically Informed Distributed Word Representations

2017-04-01 · EACL 2017 4 · Ivan Vuli{\'c}

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+7

Compositional Sentence Representation from Character within Large Context Text

2016-05-02 · Geonmin Kim, Hwaran Lee, Jisu Choi, Soo-Young Lee

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 ClassificationSentence

Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks

2018-09-12 · ACL 2019 7 · Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai 외

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 Embeddings

Dependency-based Hybrid Trees for Semantic Parsing

2018-09-01 · EMNLP 2018 10 · Zhanming Jie, Wei Lu

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