Progressive fine-tuning method for speech Synthesis in Chinese news broadcasting

Guo Zijie1
Li Bicheng1
Huang Liangping1
Liao Yunbao2
1. Huaqiao University College of Computer Science and Technology Xiamen Fujian 361021, China
2. College of Computer & Network Security, Chengdu University of Technology, Chengdu Sichuan 610059, China

Abstract

Pre-trained text-to-speech (TTS) models often exhibit mismatched training and inference conditions and insufficient prosodic structure during domain fine-tuning. ProNews-TTS (Progressive News TTS) addresses these issues through three stages. First, condition-alignment fine-tuning reduces the training-inference mismatch. Next, a prosody adapter injects pause and intonation cues. Finally, style contrastive learning enforces speaker-style consistency. Experiments showed that ProNews-TTS achieved a character error rate of 2.58%, a word error rate of 4.68%, a prosody score of 63.25, and a speaker-similarity score of 0.671. Compared with the official CosyVoice2-0.5B baseline, it reduced CER by 6.38 percentage points and WER by 9.16 percentage points, while increasing the prosody score by 8.09 and speaker similarity by 0.015. The third stage updated only 0.642M parameters, approximately 0.1% of the full system. ProNews-TTS achieves joint adaptation of content, prosody, and speaker style with limited parameter updates.

Foundation Support

厦门市科技计划项目(3502Z20241029)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.05.0136
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-08-28] Accepted Paper

Cite This Article

郭子杰, 李弼程, 黄良平, 等. 面向中文新闻播报场景的渐进式语音合成微调方法 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.05.0136. (Guo Zijie, Li Bicheng, Huang Liangping, et al. Progressive fine-tuning method for speech Synthesis in Chinese news broadcasting [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.05.0136. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.


Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)