Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language
复制标题
DOI：
--
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Kohei Matsuura;Sei Ueno;M. Mimura;S. Sakai;T. Kawahara
中科院分区：
文献类型：
--
作者：
Kohei Matsuura;Sei Ueno;M. Mimura;S. Sakai;T. Kawahara
阿伊努语是一种不成文的语言，由日本少数民族之一的阿伊努人使用。它被联合国教科文组织认定为极度濒危物种，对其语言遗产的归档和记录至关重要。尽管为了拯救阿伊努文化而制作和积累了大量的阿伊努民间传说录音，但迄今为止只有相当有限的部分被转录。因此，我们启动了阿伊努语自动语音识别（ASR）项目，以便为带注释的语言档案的开发做出贡献。在本文中，我们报告了阿伊努语语音语料库的开发以及端到端 ASR 的结构和性能。我们研究了四个建模单元（音素、音节、词段和单词），发现基于音节的模型在单词和音素识别准确率方面表现最好，在扬声器开放条件下分别约为 60% 和超过 85%。此外，在扬声器关闭的情况下，单词和电话的准确率已达到 80% 和 90%。我们还发现，使用额外的英语和日语语音语料库进行多语言 ASR 训练进一步提高了说话人开放测试的准确性。
Ainu is an unwritten language that has been spoken by Ainu people who are one of the ethnic groups in Japan. It is recognized as critically endangered by UNESCO and archiving and documentation of its language heritage is of paramount importance. Although a considerable amount of voice recordings of Ainu folklore has been produced and accumulated to save their culture, only a quite limited parts of them are transcribed so far. Thus, we started a project of automatic speech recognition (ASR) for the Ainu language in order to contribute to the development of annotated language archives. In this paper, we report speech corpus development and the structure and performance of end-to-end ASR for Ainu. We investigated four modeling units (phone, syllable, word piece, and word) and found that the syllable-based model performed best in terms of both word and phone recognition accuracy, which were about 60% and over 85% respectively in speaker-open condition. Furthermore, word and phone accuracy of 80% and 90% has been achieved in a speaker-closed setting. We also found out that a multilingual ASR training with additional speech corpora of English and Japanese further improves the speaker-open test accuracy.