Breeze Taigi：台湾台语语音识别与合成的基准与模型
Breeze Taigi: Benchmarks and Models for Taiwanese Hokkien Speech Recognition and Synthesis
AI总结：
本文提出Breeze Taigi框架，通过标准化基准评估台语语音识别与合成系统，提供30对精心挑选的台语与普通话音频对，并采用字符错误率作为标准指标，展示了基于现有资源和合成数据的模型训练方法，实现了30.13%的平均CER。
摘要：
台湾台语（Taigi）为推进能泛化至多样化语言环境的语音技术方法提供了独特机会。我们引入Breeze Taigi，一个以标准化基准为核心的框架，用于评估台语语音识别和合成系统。我们的主要贡献是可复现的评估方法，利用平行的台湾普通话资源。我们提供了30对精心挑选的普通话-台语音频对，来自台湾行政院的公共广播公告，并提供标准化的转录文本。我们建立了字符错误率（CER）作为标准度量，并实施归一化程序以实现公平的跨系统比较。为展示基准的效用并提供参考实现，我们通过利用现有台湾普通话资源和大规模合成数据生成的方法开发语音识别和合成模型。特别是，我们对Whisper模型进行了约10,000小时的台语合成语音数据的微调。我们的ASR模型在基准上实现了30.13%的平均CER，优于现有商业和研究系统。通过提供标准化评估协议、多样化的训练数据集和开放的基础模型，我们提供了一个可复现的框架，其方法适用于各种语言环境。
英文摘要：
Taiwanese Hokkien (Taigi) presents unique opportunities for advancing speech technology methodologies that can generalize to diverse linguistic contexts. We introduce Breeze Taigi, a comprehensive framework centered on standardized benchmarks for evaluating Taigi speech recognition and synthesis systems. Our primary contribution is a reproducible evaluation methodology that leverages parallel Taiwanese Mandarin resources. We provide 30 carefully curated Mandarin-Taigi audio pairs from Taiwan's Executive Yuan public service announcements with normalized ground truth transcriptions. We establish Character Error Rate (CER) as the standard metric and implement normalization procedures to enable fair cross-system comparisons. To demonstrate the benchmark's utility and provide reference implementations, we develop speech recognition and synthesis models through a methodology that leverages existing Taiwanese Mandarin resources and large-scale synthetic data generation. In particular, we fine-tune a Whisper model on approximately 10,000 hours of Taigi synthetic speech data. Our ASR model achieves 30.13% average CER on the benchmark, outperforming existing commercial and research systems. By providing standardized evaluation protocols, diverse training datasets, and open baseline models, we offer a replicable framework with methodologies applicable to various linguistic contexts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
