arXiv 2306.044282023-06-13cs.CLcs.SDeess.AS

Zambezi Voice：面向赞比亚语言的多语言语音语料库

Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages

University of Zambia（赞比亚大学）；George Mason University（乔治梅森大学）

Claytone Sikasote, Kalinda Siaminwe, Stanly Mwape, Bangiwe Zulu, Mofya Phiri, Martin Phiri, David Zulu, Mayumbo Nyirenda, Antonios Anastasopoulos

备注：: Accepted at INTERSPEECH 2023. This pre-print version differs slightly from the version accepted to INTERSPEECH 2023: Figure 1 is not included in INTERSPEECH 2023!

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究推出首个面向赞比亚语言的开源多语言语音语料库Zambezi Voice，含160小时未标注与超80小时标注语音数据，通过微调Wav2Vec2.0构建语音识别基线模型，数据集已公开发布。

摘要：

本研究推出Zambezi Voice，这是一款面向赞比亚语言的开源多语言语音资源。它包含两类数据集集合：来自广播新闻和脱口秀节目的未标注音频录音（160小时），以及由公开文学书籍文本录制的朗读语音构成的标注数据（超80小时）。该数据集为语音识别任务构建，也可拓展用于有监督和无监督学习范式下的多语言语音处理研究。据我们所知，这是首个为赞比亚语言创建的多语言语音数据集。我们利用预训练与跨语言迁移学习，对Wav2Vec2.0大规模多语言预训练模型进行微调，构建端到端（E2E）语音识别模型作为基线模型。该数据集以知识共享BY-NC-ND 4.0协议公开发布，可通过https://github.com/unza-speech-lab/zambezi-voice 获取。

英文摘要：

This work introduces Zambezi Voice, an open-source multilingual speech resource for Zambian languages. It contains two collections of datasets: unlabelled audio recordings of radio news and talk shows programs (160 hours) and labelled data (over 80 hours) consisting of read speech recorded from text sourced from publicly available literature books. The dataset is created for speech recognition but can be extended to multilingual speech processing research for both supervised and unsupervised learning approaches. To our knowledge, this is the first multilingual speech dataset created for Zambian languages. We exploit pretraining and cross-lingual transfer learning by finetuning the Wav2Vec2.0 large-scale multilingual pre-trained model to build end-to-end (E2E) speech recognition models for our baseline models. The dataset is released publicly under a Creative Commons BY-NC-ND 4.0 license and can be accessed via https://github.com/unza-speech-lab/zambezi-voice .

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。