当前的图像检索的技术中主要基于两种方式,基于内容技术和基于文本技术,但是基于图像或基于文本的技术只是依靠低层视觉特征、高层语义特征来进行检索,具有很大的局限性,图像检索的效率也不高,而语音识别技术在图像检索中使用作为一种新的形式,取得了高效的检索结果。而研究语音识别技术在图像检索中的应用,可以提升其应用水平,为相关研究做出一定的贡献。 The current image retrieval technology is mainly based on two methods, based on content technology and text-based technology, but image-based or text-based technology only relies on low-level visual features, high-level semantic features to retrieve, has great limitations, the image Retrieval efficiency is not high, and speech recognition technology used in image retrieval as a new form, and achieved efficient retrieval results. The application of speech recognition technology in image retrieval can improve its application level and make some contributions to related research.