Results 1 - 4 of 4

The Similar Segments in Social Speech Task

by Nigel G. Ward, Steven D. Werner, David G. Novick, Elizabeth E. Shriberg, Catharine Oertel, Tatsuya Kawahara , 2013
"... Similar Segments in Social Speech was one of the Brave New Tasks at MediaEval 2013. The task involves finding segments similar to a query segment, in a multimedia collection of informal, unstructured dialogs among members of a small community. Categories and Subject Descriptors ..."
Abstract - Cited by 5 (4 self) - Add to MetaCart
Similar Segments in Social Speech was one of the Brave New Tasks at MediaEval 2013. The task involves finding segments similar to a query segment, in a multimedia collection of informal, unstructured dialogs among members of a small community. Categories and Subject Descriptors
(Show Context)

Data collection for the Similar Segments in Social Speech task.

by Nigel G Ward , Steven D Werner , 2013
"... Information retrieval systems rely heavily on models of similarity, but for spoken dialog such models currently use mostly standard textual-content similarity. As part of the MediaEval Benchmarking Initiative, we have created a new corpus to support development of similarity models for spoken dialo ..."
Abstract - Cited by 3 (3 self) - Add to MetaCart
Information retrieval systems rely heavily on models of similarity, but for spoken dialog such models currently use mostly standard textual-content similarity. As part of the MediaEval Benchmarking Initiative, we have created a new corpus to support development of similarity models for spoken dialog. This corpus includes 26 casual dialogs among members of two semi-cohesive groups, totaling about 5 hours, with 1889 labeled regions associated into 227 sets which annotators judged to be similar enough to share a tag. This technical report brings together information about this corpus and its intended uses, previously only available on the project website.

Evaluating Prosody-Based Similarity Models for Information Retrieval

by Steven D. Werner, Nigel G. Ward
"... Prosody is important in spoken language, and especially in dialog, but its utility for search in dialog archives has remained an open question. Using prosody-based measures of similarity, which also roughly correlate with dialog-activity similarity and topic similarity, we built support for “retriev ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
Prosody is important in spoken language, and especially in dialog, but its utility for search in dialog archives has remained an open question. Using prosody-based measures of similarity, which also roughly correlate with dialog-activity similarity and topic similarity, we built support for “retrieve more like this ” searches. Performance on the Similar Segments in Social Speech Task at MediaEval 2013 was well above baseline, showing the value of prosody for search. 1.
(Show Context)

A prosody-based vectorspace model of dialog activity for information retrieval

by Nigel G Ward , Steven D Werner , Fernando Garcia , Emilio Sanchis - Speech Communication , 2015
"... Abstract Search in audio archives is a challenging problem. Using prosodic information to help find relevant content has been proposed as a complement to word-based retrieval, but its utility has been an open question. We propose a new way to use prosodic information in search, based on a vector-sp ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
Abstract Search in audio archives is a challenging problem. Using prosodic information to help find relevant content has been proposed as a complement to word-based retrieval, but its utility has been an open question. We propose a new way to use prosodic information in search, based on a vector-space model, where each point in time maps to a point in a vector space whose dimensions are derived from numerous prosodic features of the local context. Point pairs that are close in this vector space are frequently similar, not only in terms of the dialog activities, but also in topic. Using proximity in this space as an indicator of similarity, we built support for a query-by-example function. Searchers were happy to use this function, and it provided value on a large testset. Prosody-based retrieval did not perform as well as word-based retrieval, but the two sources of information were often non-redundant and in combination they sometimes performed better than either separately.
(Show Context)