蒙古语多方言语音识别及共享识别模型探索

Inquiry into a Common Acoustic Model to Realize Mongolian Dialectal Speech Recognition

通过语音输入方式准确识别蒙古语主要方言 ,并为其建立共享识别模型 ,对实现方言间的信息自动交换及语音识别技术的实用化具有实际意义。针对蒙古语多方言的语音特点 ,可以采取独立的或者共享识别模型进行识别。本文介绍的抽出初步模型和建立共享模型的方法 ,简便易行 ,但识别精度有待提高。文中探索了通过借用数据量和质较完备的语言的语音数据提高识别率的可能性。

It is easy to establish an initial model and common used model,but it is not accurate for speech recognition.It is possible to do the recognition by using good in quantity and quality phonetic data.To do speech recognition of Mongolian language by way of phonetic introduction and to establish common used model is practical for information exchange between dialects and speech recognition.As the Mongolian language has multi dialects,it is possible to use individual or common used model to make the speech recognition. [