针对台湾腔中文混用语音，构建高效分词与语言模型，显著提升合成质量。
BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech
- 用台湾语料训练字节级分词器，减少51.5%的分词数量。
- 在台湾本地测试集上，语音识别错误率降低63.9%。
- 适合需要高保真台湾腔语音合成的研究者与开发者。
现成的语音合成系统对台湾普通话适应性差，普遍存在口音偏差、分词过度及中英混用边界发音劣化问题。根源在于文本处理未适配台湾语境。本文从底层重构：PangolinTokenizer是基于台湾语料训练的字节级BPE分词器，在九种分词器中达到最低的0.485词元/字符比和最小词表规模；Barbet是基于该分词器训练的十亿参数繁体中文语言模型，在14项任务评估中表现最优；BlueMagpie-TTS通过可学习桥接模块将Barbet接入VoxCPM2预训练声学栈，保持声学部分不变。在1000句台湾本地化测试集上，字符错误率（CER）从11.45%降至4.81%，词错误率（WER）从14.83%降至5.36%，相对降低58.0%和63.9%。盲听实验中，500句由10名听众评估，65.6%的多数投票偏好BlueMagpie-TTS。
原文摘要 · Abstract (English)
Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text side from the bottom up. PangolinTokenizer, a byte-level BPE tokenizer trained on Taiwan-context data, reaches the lowest token rate (0.485 tokens/character) with the smallest vocabulary among nine tokenizers. Barbet, a billion-parameter Traditional-Chinese language model trained on PangolinTokenizer, serves as the text-semantic frontend and ranks first among comparable public models on a 14-task evaluation. BlueMagpie-TTS attaches Barbet to the pretrained acoustic stack of VoxCPM2 through a learned bridge, keeping the acoustic stack fixed. On a 1000-sentence Taiwan-localized test set, it lowers CER from 11.45% to 4.81% and WER from 14.83% to 5.36%, relative reductions of 58.0% and 63.9%. In a blind listening study on 500 of these sentences with ten listeners, 65.6% of majority votes prefer BlueMagpie-TTS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。