For non-native learners of Chinese,correct pronunciation is a difficult task,and traditional pronunciation teaching methods are difficult to visualize the movement process of pronunciation.Therefore,this study enables learners to visualize the move-ments of lips and tongue by applying sensor technology to capture and transform the pronunciation process,so that they can better imi-tate and improve pronunciation.The experimental results show that the audio signals acquired by the sensor have low noise interfer-ence and good quality,and there is a good linear relationship between the output electrical signal and the sound pressure.The experi-mental system performs well in terms of recognition of sound signals and laryngeal and neck movements with an accuracy of more than 80％,and finally the visual synthesis effect is successfully achieved,and the pronunciation accuracy of the teaching class applying the method reaches up to 0.9.In conclusion,the 3D pronunciation visual synthesis system based on the sensor technology provides an ef-fective tool and methodology for pronunciation research and teaching,and is expected to have a have a positive impact.
关键词
声音传感器/发音识别/三维可视化/合成系统
Key words
sound sensors/articulation recognition/3D visualisation/synthesis system
维普
万方数据