DANTE Speaker Recognition Module. An Efficient and Robust Automatic Speaker Searching Solution for Terrorism-Related Scenarios
The vast amount of data crossing the net with terrorism-related content, including voice, is so immense that the use of powerful filtering/detection tools with great discriminative capacities becomes essential. Although the analysis of this content often ends with some manual inspection, a first filtering process becomes basic. In this direction, we propose a speaker clustering solution based on a speaker identification system. We show that both the speaker clustering and the speaker recognition solution can be used individually to efficiently solve searching tasks in several terrorism-related scenarios.
KeywordsAutomatic speaker recognition Speaker identification Speaker verification Automatic speaker clustering
The work presented in this paper was supported by the European Commission under contract H2020-700367 DANTE .
- 1.DANTE project homepage. http://www.h2020-dante.eu/. Accessed July 2018
- 4.Tryon, R.: Clustering Analysis (1993)Google Scholar
- 7.Cumani, S., Laface, P.: Training pairwise support vector machines with large scale datasets. In: 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2014, Florence (Italy), pp. 1664–1668 (2014)Google Scholar
- 9.Lei, Y., Scheffer, N., Ferrer, L., McLaren, M.: A novel scheme for speaker recognition using a phonetically-aware deep neural network. In: Proceedings of ICASSP 2014, pp. 1714–1718 (2014)Google Scholar
- 10.Cumani, S., Batzu, P.D., Colibro, D., Vair, C., Laface, P., Vasilakakis, V.: Comparison of speaker recognition approaches for real applications. In: Interspeech 2011, Florence, Italy, pp. 2365–2368 (2011)Google Scholar
- 12.Leeuwen, D.A.V.: Speaker linking in large datasets. In: Odyssey 2010, the Speaker Language and Recognition Workshop, Brno, Czech Republic, pp. 202–208 (2010)Google Scholar
- 13.Jorrín-Prieto, J.., Vaquero, C., García, P.: Analysis of the impact of the audio database characteristics in the accuracy of a speaker clustering system. In: Odyssey 2016, the Speaker Language and Recognition Workshop, Bilbao, Spain, pp. 393–399 (2016)Google Scholar
- 14.Bolle, R.M., Connell, J.H., Pankanti, S., Ratha, N.K., Senior, A.W.: The relation between the ROC curve and the CMC. In: Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID 2005), pp. 15–20 (2005)Google Scholar