arXiv cs.CL· Kola Tubosun, Adedayo Oluokun, Hafiz Adewuyi, Dadepo Aderemi·· 12 小时前AI 评分18
TTSYoruba：面向约鲁巴语的规则化双音素语音合成系统
A Situational Speech Synthesizer for Yoruba: System Design, Phonological Rule Architecture, and Orthographic Extensions for Contour
AI 导读
TTSYoruba 是一个基于规则拼接双音素的约鲁巴语语音合成系统，已上线于约鲁巴语人名开放词典网站，输入带声调标记的文本即可输出音频。系统使用 651 个双音素单元，覆盖该语言每个辅音-元音组合的五种声调变体，并采用 caron 与 circumflex 作为单元音曲拱声调标记，集成进 TTS 归一化流程和 WriteYoruba 键盘工具。
正文 · 原文
Abstract:We present TTSYoruba, a rule-based concatenative diphone speech synthesizer for Yoruba, deployed at online as part of the this http URL open dictionary of Yoruba personal names. The system takes tone-marked Yoruba text as input and produces audio output by applying a hand-crafted phonological rule system to a recorded inventory of 651 diphone units spanning five tonal variants of every consonant-vowel combination in the language. We describe the phonological architecture of the system in detail, including our complete tonal file-selection logic, our treatment of the three-way nasal disambiguation problem (oral /n/, nasalized vowel, and syllabic nasal), and the derivation of contextual rising and falling tones from level-tone input. We also present, as an orthographic contribution, the adoption of the caron and circumflex, which are symbols with prior standing in Yoruba phonological transcription, as standard single-vowel contour tone markers, integrated into the TTS normalization pipeline and the WriteYoruba keyboard input tool. The system's performance was evaluated through a listener study (N=50), with detailed results on Mean Opinion Scores (MOS) presented in Section 6.
Keywords: Yoruba, text-to-speech, low-resource languages, diphone synthesis, contour tones, African language NLP, rule-based synthesis
| Comments: | 18 pages, 6 tables. This version: corrects the description of Iyanda et al. (2014) and the date of Odejobi et al. (2007); adds discussion of earlier Yoruba grapheme-to-phoneme work and of Abraham (1958); cites the reference keyboard mapping (doi:https://doi.org/10.5281/zenodo.23305200%29%3B formatting corrections |
| Subjects: | Sound (cs.SD); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS) |
| ACM classes: | I.2.7; H.5.5 |
| Cite as: | arXiv:2607.18317 [cs.SD] |
| (or arXiv:2607.18317v5 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2607.18317 arXiv-issued DOI via DataCite |
Submission history
From: Kola Tubosun [view email]
[v1]
Fri, 17 Jul 2026 20:13:41 UTC (388 KB)
[v2]
Thu, 23 Jul 2026 00:00:02 UTC (378 KB)
[v3]
Thu, 1 Oct 2026 15:56:05 UTC (19 KB)
[v4]
Sun, 11 Oct 2026 17:32:03 UTC (19 KB)
[v5]
Fri, 16 Oct 2026 16:23:21 UTC (19 KB)
来源：arXiv cs.CL · arxiv.org