This study analyses the acoustic productions in the acquisition of Chinese vowels by the learners from ‘the Belt and Road’, i.e., Uzbek learners and Xinjiang Uyghur learners who are in the same cross-border language (Uzbek and Uyghur). The acoustic differences in vowel acquisition between the two types of learners were comparatively analyzed, and the following conclusions were drawn: in the acquisition of diphthongs, both Uzbek and Xinjiang Uyghur learners had problems with tongue sliding and tip position control. Their tongue position changes during pronunciation were not natural enough. Overall, Xinjiang Uyghur learners performed better than Uzbek learners. This comparative study reveals the common and differentiated features of learners’ acquisition of Chinese phonetic, so as to provide a theoretical grounding and practical guidance for a more effective Chinese language education.