Using Acoustic Diarization for Duplicate Detection
Title | Using Acoustic Diarization for Duplicate Detection |
Publication Type | Technical Report |
Year of Publication | 2012 |
Authors | Knox, M. Tai, Friedland G., & R. Smith P. |
Other Numbers | 3273 |
Abstract | The following article describes the use of an acoustic diarization engine for duplicatedetection on broadcast news. Diarization is typically used to partition audio into speakerhomogeneous regions, or in other words, to determine who spoke when. In thissetting, however, we use diarization to segment the recordings and group the segmentsinto homogeneous clusters. Diarization is performed both on the full length broadcastnews recordings as well as the short clips (which we are classifying as either a duplicateor not). We then compare the similarity of models trained on the clusters to determinewhether the time allocated to the cluster from the short clip is from the originalbroadcast news recording, or a duplicate. We tested our system under a variety of audioconditions: unmodified, with reverberation, resampled, and lowpass filtered. On ourtest set, the areas under the receiver operating characteristic curve for the audioconditions were 0.91, 0.89, 0.61, and 0.64 respectively. |
URL | http://www.icsi.berkeley.edu/pubs/techreports/TR-12-005.pdf |
Bibliographic Notes | ICSI Technical Report TR-12-005 |
Abbreviated Authors | M. Knox, G. Friedland, and R. P. Smith |
ICSI Research Group | Speech |
ICSI Publication Type | Technical Report |