DeepAI AI Chat
Log In Sign Up

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

by   Junjie Pan, et al.
ByteDance Inc.

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).


page 1

page 2

page 3

page 4


Tacotron: Towards End-to-End Speech Synthesis

A text-to-speech synthesis system typically consists of multiple stages,...

Unified Mandarin TTS Front-end Based on Distilled BERT Model

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

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

We propose a novel phrase break prediction method that combines implicit...

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...

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

The accuracy of prosodic structure prediction is crucial to the naturaln...

Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit

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