Automatic Speech Recognition for Uyghur, Kazakh, and Kyrgyz: An Overview

With the emergence of deep learning, performance automatic speech recognition (ASR) systems has remarkably improved. Especially for resource-rich languages such as English and Chinese, commercial usage been made feasible in a wide range applications. However, most are low-resource languages, presenting three main difficulties development ASR systems: (1) scarcity data; (2) uncertainty writing pronunciation; (3) individuality each language. Uyghur, Kazakh, Kyrgyz examples all involving clear geographical variation their pronunciation, language possesses its own unique acoustic properties phonological rules. On other hand, they belong to Altaic family branch, so share many commonalities. This paper presents an overview techniques developed Kyrgyz, with purposes highlighting that specifically effective generally them discovering important factors promoting research by comparative study path these neighboring languages.