ISCA Archive SPSC 2021
ISCA Archive SPSC 2021

Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data

Maël Fabien, Seyyed Saeed Sarfjoo, Petr Motlicek, Srikanth Madikeri

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 central characters and the different communities within the network. This paper introduces a new method, Graph2Speak, to re-rank individuals after applying a speaker identification step, by leveraging the frequency of previous interactions extracted from a graph. We deploy our method on two candidate datasets for criminal conversational data, Crime Scene Investigation (CSI), a television show, and the ROXANNE simulated data. We demonstrate that our method can reduce the error rates of the speaker identification baseline by up to 12% (relative).


doi: 10.21437/SPSC.2021-3

Cite as: Fabien, M., Sarfjoo, S.S., Motlicek, P., Madikeri, S. (2021) Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data. Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication, 10-13, doi: 10.21437/SPSC.2021-3

@inproceedings{fabien21_spsc,
  author={Maël Fabien and Seyyed Saeed Sarfjoo and Petr Motlicek and Srikanth Madikeri},
  title={{Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data}},
  year=2021,
  booktitle={Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication},
  pages={10--13},
  doi={10.21437/SPSC.2021-3}
}