Developing Speech Resources from Parliamentary Data for South African English

详细信息    查看全文

• 作者：Febe de Wet ; ^{fdwet@csir.co.za" class="auth_mail" title="E-mail the corresponding author} ; Jaco Badenhorst ; Thipe Modipa
• 关键词：Under-resourced languages ; speech data ; South African English ; automatic alignment.
• 刊名：Procedia Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：81
• 期：Complete
• 页码：45-52
• 全文大小：373 K

文摘

The official languages of South Africa can still be classified as under-resourced with respect to the speech resources that are required for technology development. Harvesting speech data from existing sources is one means to create additional resources. The aim of the study reported on in this paper was to improve the harvesting and transcription accuracy of a corpus derived from parliamentary data. This aim was achieved by improving on the text normalisation process and pronunciation modelling as well as by iteratively training more accurate in-domain acoustic models. In this manner, more data could be harvested with higher confidence than using baseline pronunciation dictionaries and out-of-domain speech data.