Robust Voice Mining Techniques for Telephone Conversations
dc.contributor.advisor | Espy-Wilson, Carol Y. | en_US |
dc.contributor.author | Manocha, Sandeep | en_US |
dc.contributor.department | Electrical Engineering | en_US |
dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
dc.date.accessioned | 2006-09-12T05:51:05Z | |
dc.date.available | 2006-09-12T05:51:05Z | |
dc.date.issued | 2006-07-28 | en_US |
dc.description.abstract | Voice mining involves speaker detection in a set of multi-speaker files. In published work, training data is used for constructing target speaker models. In this study, a new voice mining scenario was considered, where there is no demarcation between training and testing data and prior target speaker models are absent. Given a database of telephone conversations, the task is to identify conversations having one or more speakers in common. Various approaches including semi-automatic and fully automatic techniques were explored and different scoring strategies were considered. Given the poor audio quality, automatic speaker segmentation is not very effective. A new technique was developed which does not require speaker segmentation by training a multi-speaker model on the entire conversation. This technique is more robust and it outperforms the automatic speaker segmentation approach. On the ENRON database, the EER is 15.98% and 6.25% for at least one and two speakers in common, respectively. | en_US |
dc.format.extent | 1302693 bytes | |
dc.format.mimetype | application/pdf | |
dc.identifier.uri | http://hdl.handle.net/1903/3827 | |
dc.language.iso | en_US | |
dc.subject.pqcontrolled | Engineering, Electronics and Electrical | en_US |
dc.subject.pquncontrolled | voice mining | en_US |
dc.subject.pquncontrolled | speaker detection | en_US |
dc.subject.pquncontrolled | speaker recognition | en_US |
dc.title | Robust Voice Mining Techniques for Telephone Conversations | en_US |
dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1