# CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation

arXiv: https://arxiv.org/abs/2606.24714 · HTML: https://mlsanity.com/paper/2606.24714/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 5 of 5)

- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [RNN Approaches to Text Normalization: A Challenge](https://mlsanity.com/paper/1611.00068/) (2016)
- [g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset](https://mlsanity.com/paper/2004.03136/) (2020)
- [An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer](https://mlsanity.com/paper/2203.16954/) (2022)

## Abstract (arXiv)

Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mixed Chinese-Latin-digit names. These forms are frequent in real listening workflows, and a text-to-speech (TTS) system can preserve the written string while changing the spoken meaning. We introduce CN-NewsTTS Bench v0.1, an open target-level benchmark for evaluating whether Chinese news TTS products pronounce such targets correctly from raw text, without user-side rules, LLM rewriting, SSML hints, or manual edits. The release contains a 200-record development set, an 800-record public test set, 992 public auto-evaluable targets, fixed transcripts from a three-ASR ensemble, an automatic target scorer, and initial results for seven product TTS systems. We additionally report ASR-route diagnostics, ASR-subset ablations, category-level results, confidence intervals, and provider configuration metadata. The best system reaches 0.879 strict accuracy, while several systems remain below 0.60.