Klara Weiand

Similarity Visualization for the Grouping of Forensic Speech Recordings

In a forensic phone wiretapping investigation, a major problem is to get the full picture of the speakers involved. Typically, the wiretapped speech recordings are grouped using a clustering tool. The main disadvantage of such an approach is that in a bootstrapped scenario grouping errors accumulate. In this paper, we propose a visual approach to find similar speech recordings that probably stem from the same speaker. We first model the speech recordings and define suitable similarity measures between recordings. Then, through an approximate 2-D visualization of the inter-speech, similarities the investigator can identify clear groups of recordings and recordings that are harder to differentiate. We did extensive experiments on phone data of 50 speakers with 2 recordings per speaker. We tested quality of the 2-D visualization in relation to original high dimensional similarities. It turned out that for the original high dimensional similarity measure the nearest recording is almost always the one from the same speaker. In the 2-D visualization, we achieved that on average for all speech recordings a recording of the same speaker is among the 10 nearest recordings.

Keyword-Based Search over Semantic Data

Enabling nonexperts to publish structured or semantic data on the web is an important achievement of the social web and one of the primary goals of the social semantic web. Making this data easily accessible in turn has received only little attention. Querying in semantic wikis typically uses full-text search for the textual content and a web query language for the annotations. This has two shortcomings: combined queries over content and annotations are not possible, and users either are restricted to simple but vague keyword queries or have to learn a complex web query language. In this chapter, we present an overview of KWQL, a query language that combineskeyword search and web querying. KWQL scales with a users’ experience and the sophistication of its information need by a seamless transition from basic keyword queries to precise, sophisticated structured analysis queries. KWQL allows for rich combined queries of full text, metadata, document structure, and annotations. KWQL’s companion language visKWQL eases the authoring of such combined queries further through a set of visual building blocks. The underlying query engine provides the full expressive power of first-order queries, but, at the same time evaluates basic queries at almost the speed of a conventional search engine. Results of a user study validate that users can quickly, and with very little training, formulate KWQL and visKWQL queries, including structured queries.