logo Idiap Research Institute        
 [BibTeX] [Marc21]
Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data
Type of publication: Idiap-RR
Citation: Fabien_Idiap-RR-01-2023
Number: Idiap-RR-01-2023
Year: 2023
Month: 1
Institution: Idiap
Address: 19 rue Marconi, 1920 Lausanne
Abstract: Criminal investigations mostly rely on the collection of speech conversational data in order to identify speakers and build or enrich an existing criminal network. Social network analysis tools are then applied to identify the most central characters and the different communities within the network. We introduce two candidate datasets for criminal conversational data, Crime Scene Investigation (CSI), a television show, and the ROXANNE simulated data. We also introduce the metric of conversation accuracy in the context of criminal investigations. By re-ranking candidate speakers based on the frequency of previous interactions, we improve the speaker identification baseline by 1.2% absolute (1.3% relative), and the conversation accuracy by 2.6% absolute (3.4% relative) on CSI data, and by 1.1% absolute (1.2% relative), and 2% absolute (2.5% relative) respectively on the ROXANNE simulated data.
URL: https://arxiv.org/abs/2006.020...
Projects Idiap
Authors Fabien, Mael
Sarfjoo, Seyyed Saeed
Madikeri, Srikanth
Motlicek, Petr
Crossref by Sarfjoo_SPSC_2021
Added by: [ADM]
Total mark: 0
  • Fabien_Idiap-RR-01-2023.pdf (MD5: d6f5da077c20b59a4b4560bb50457389)