DeepAI AI Chat
Log In Sign Up

A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis

11/11/2019
by   Junjie Pan, et al.
ByteDance Inc.
0

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple individual components requires extensive efforts. In this paper, we proposed a unified sequence-to-sequence front-end model for Mandarin TTS that converts raw texts to linguistic features directly. Compared to the pipeline-based front-end, our unified front-end can achieve comparable performance in polyphone disambiguation and prosody word prediction, and improve intonation phrase prediction by 0.0738 in F1 score. We also implemented the unified front-end with Tacotron and WaveRNN to build a Mandarin TTS system. The synthesized speech by that got a comparable MOS (4.38) with the pipeline-based front-end (4.37) and close to human recordings (4.49).

READ FULL TEXT

page 1

page 2

page 3

page 4

03/29/2017

Tacotron: Towards End-to-End Speech Synthesis

A text-to-speech synthesis system typically consists of multiple stages,...
12/31/2020

Unified Mandarin TTS Front-end Based on Distilled BERT Model

The front-end module in a typical Mandarin text-to-speech system (TTS) i...
04/26/2021

Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis

We propose a novel phrase break prediction method that combines implicit...
05/20/2020

Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis

Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce h...
03/31/2022

A Character-level Span-based Model for Mandarin Prosodic Structure Prediction

The accuracy of prosodic structure prediction is crucial to the naturaln...
08/13/2020

Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit

Recent neural speech synthesis systems have gradually focused on the con...