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

arXiv: https://arxiv.org/abs/1911.04111 · HTML: https://mlsanity.com/paper/1911.04111/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Review of end-to-end speech synthesis technology based on deep learning](https://mlsanity.com/paper/2104.09995/) (2021)
- [A unified front-end framework for English text-to-speech synthesis](https://mlsanity.com/paper/2305.10666/) (2023)
- [Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language](https://mlsanity.com/paper/2212.08321/) (2022)
- [Multilingual context-based pronunciation learning for Text-to-Speech](https://mlsanity.com/paper/2307.16709/) (2023)
- [Grapheme-Coherent Phonemic and Prosodic Annotation of Speech by Implicit and Explicit Grapheme Conditioning](https://mlsanity.com/paper/2506.04527/) (2025)
- [Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning](https://mlsanity.com/paper/2409.09891/) (2024)
- [AMNet: An Acoustic Model Network for Enhanced Mandarin Speech Synthesis](https://mlsanity.com/paper/2504.09225/) (2025)

## Abstract (arXiv)

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).