Metadata for integrating speech documents in a text retrieval system

Abstract

We present an information retrieval system that simultaneously allows to search for text and speech documents. The retrieval system accepts vague queries and performs a best-match search to find those documents that are relevant to the query. The output of the retrieval system is a list of ranked documents where the documents on the top of the list satisfy best the user's information need. The relevance of the documents is estimated by means of metadata (document description vectors). The metadata is automatically generated and it is organized such that queries can be processed efficiently. We introduce a controlled indexing vocabulary for both speech and text documents. The size of the new indexing vocabulary is small (1000 features) compared with the sizes of indexing vocabularies of conventional text retrieval (10000 -100000 features). We show that the retrieval effectiveness based on such a small indexing vocabulary is similar to the retrieval effectiveness of a Boolean retrieval system.

Automatic Summarization

“…With the notable exception of the work at ETH Zürich [87,88], the early work on SCR was devoted to English language spoken content. Retrieval of English language content is relatively simple, since features to be searched in the form of words are readily available.…”

The Semantic Web

“…NDVI and spatial registration metadata were used to model geospatial maps, primarily of different types of vegetation [30]. Interesting examples of mixed-media access are the speech feature index [23] and topic change indices [20]. Metadata capturing information about documents are document vectors [22], inverted indices [25], document classification and composition metadata [19] and parent-child relationships (based on document structure) [31].…”

“…The Semantic Web Services Architecture (SWSA) is a product of the Semantic Web Services Initiative (SWSI), 23 "an ad hoc initiative of academic and industrial researchers, many of which are involved in DARPA and EU funded research projects". SWSI had two aims: the creation of a Semantic Web Services Language (SWSL) which we discussed as part of Section 11.3.2 on the Semantic Web Services Framework (a W3C member submission), and the development of a Semantic Web Services Architecture (SWSA) [290].…”

Cross-language speech retrieval

“…It turned out however, that training and tuning the recognition system for this approach would involve substantial manual effort. The results published are therefore based on simulated experiments [Glavitsch et al, 1994].…”