How Many Do We Need? Exploration of the Population Size Effect on the Performance of Forensic Speaker Classification
This paper investigates how change in population size affects the reliability of the likelihood ratio (LR)-based forensic speaker classification. Using features of the long term F0 distribution, we performed LR-based speaker classification and examined its performance with population sizes from 10 to 120. The results revealed that LRs could be heavily influenced by the population data. We discovered that the reliability of LR-based evaluation of the evidence was heavily compromised if the...[Show more]
|Collections||ANU Research Publications|
|Source:||Proceedings of Interspeech 2008 incorporating SST 2008|
|01_Ishihara_How_Many_Do_We_Need?_2008.pdf||278.5 kB||Adobe PDF||Request a copy|
|02_Ishihara_How_Many_Do_We_Need?_2008.pdf||603.25 kB||Adobe PDF||Request a copy|
|03_Ishihara_How_Many_Do_We_Need?_2008.pdf||473.36 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.