Combining Subword and State-level Dissimilarity Measures for Improved Spoken Term Detection in NTCIR-11 SpokenQuery&Doc Task
Mitsuaki Makino, Atsuhiko Kai · NTCIR · 2014
In recent years, demands for distributing or searching multimedia contents are rapidly increasing and more effective method for multimedia information retrieval is desirable. In the studies on spoken document retrieval systems, much research has been presented focusing on the task of spoken term detection (STD), which locates a given search term in a large set of spoken documents. Recently, in such spoken document retrieval task, there has been increasing interest in using a spoken query not only for improving usability but also for low-resource languages which may have much errors by LVCSR systems. In this paper, we propose spoken term detection method using multiple scoring and dissimilarity measures for spoken query. Our proposed method is intended to convert the spoken query into a syllable sequence by LVCSR and do search that takes into account the acoustic dissimilarity on spoken documents’ LVCSR transcripts. The experimental results showed that our proposed system improve the performance compared to baseline system.