基于语音识别技术的维蒙藏语音产品开发及应用

Development of Uyghur, Mongolian and Tibetan speech products using speech recognition technology and the application

为使更多人了解使用少数民族语音产品,有效解决我国少数民族地区与其他区域之间的语言障碍问题,促进民族间的相互交流。通过搜集资料,以国内基于语音识别技术的维吾尔语、蒙古语、藏语的语音产品为研究对象,梳理其开发和应用情况,发现目前开发的相关产品主要集中于语音输入法、语音翻译软件和转录产品三方面,在此基础上,对产品使用产生的影响进行分析,并对相关语音产品的发展前景进行展望。

In order to make more people understand and use minority speech products, effectively solve the problem of language barrier between minority areas and other regions in China, and promote the mutual communication between ethnic groups, taking the domestic speech recognition technology based Uygur, Mongolian and Tibetan speech products as the research object, through the collection of data, combing their development and application, finds out that the current development products mainly focus on three aspects: speech input method, speech translation software and transcription. According to the research, the impact of the use of products is analyzed, and the development of related speech products is prospected.