Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS

By Haohan Guo, Frank K. Soong, Lei He, Lei Xie. 2019

31 citations recorded by the source corpus.

The end-to-end TTS, which can predict speech directly from a given sequence of graphemes or phonemes, has shown improved performance over the conventional TTS. However, its predicting capability is still limited by the acoustic/phonetic coverage of the training data, usually constrained by the training set size. To further improve the TTS quality in pronunciation, prosody and perceived naturalness, we propose to exploit the information embedded in a syntactically parsed tree where the inter-phrase/word information of a sentence is organized in a multilevel tree structure. Specifically, two key features: phrase structure and relations between adjacent words are investigated. Experimental results in subjective listening, measured on three test sets, show that the proposed approach is effective to improve the pronunciation clarity, prosody and naturalness of the synthesized speech of the baseline system.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Xinyu Yang
6. Zhaoxi Mu
7. Yizhuo Dong
8. Rui Liu

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “• Text pre-training [78, 101, 387, 140, 95, 447], which can provide better text representations by using pre-trained word embeddings or model parameters.”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “[65] used the factor parser [107] in the Stanford parser to extract the syntactic tree.”
• Modeling Prosodic Phrasing With Multi-Task Learning in Tacotron-Based TTS (2020, background): “There have been recent studies on prosody modeling for end-toend TTS system [29], for example, to improve the prosodic phrasing by using contextual information [30], and syntactic features [31].”
• Dependency Parsing based Semantic Representation Learning with Graph Neural Network for Enhancing Expressiveness of Text-to-Speech (2021, methodology): “The input of E2E-TTS systems is usually enriched by context-free syntactic information using taggers and syntax parsers [10, 11, 12].”