In this paper, we propose a new method for concurrent accuracy and computational efficiency optimization using a fuzzy clusters tree for i-vector speaker identification. The design assumptions and an algorithm for a new type of fuzzy i-vector tree construction were introduced. The obtained solution was evaluated using the NIST 2014 i-Vector Speaker Recognition Machine Learning Challenge dataset. A 15% relative equal error rate reduction for a 74% reduction in computation time was achieved when compared to the baseline with only a 5.5% relative identification rate loss for discussed tree configurations.
Al-KaltakchiM.T.S., WooW.L., DlayS.S., ChambersJ.A.Speaker identification evaluation based on the speech biometric and i-vector model using the timit and ntimit databases, In: 2017 5th International Workshop on Biometrics and Forensics (IWBF), (2017) pp. 1–6. DOI: 10.1109/IWBF.2017.7935102
2.
ApsingekarV.R. and De LeonP.L., Speaker model clustering for efficient speaker identification in large population applications, Audio, Speech, and Language Processing, IEEE Transactions on17(4) (2009), 848–853. DOI: 10.1109/TASL.2008.2010882
3.
BaraldiA. and BlondaP., A survey of fuzzy clustering algorithms for pattern recognition. i, Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on29(6) (1999), 778–785. DOI: 10.1109/3477.809032
4.
BimbotF., BonastreJ.F., FredouilleC., GravierG., Magrin-ChagnolleauI., MeignierS., MerlinT., Ortega-GarcíaJ., Petrovska-DelacrétazD. and ReynoldsD.A., A tutorial on textindependent speaker verification, EURASIP Journal on Applied Signal Processing2004 (2004), 430–451. DOI: https://doi.org/10.1155/S1110865704310024
5.
CampbellJ.P., Jr, Speaker recognition: A tutorial, Proceedings of the IEEE85(9) (1997), 1437–1462. DOI: 10.1109/5.628714
6.
ChaudhariU.V., NavrratilJ., RamaswamyG.N., MaesS.H., Very large population text-independent speaker identification using transformation enhanced multi-grained models. In: Acoustics, Speech, and Signal Processing, 2001 Proceedings(ICASSP’01) 2001 IEEE International Conference on IEEE, vol. 1, 2001, 461–464. DOI: 10.1109/ICASSP.2001.940867.
7.
CumaniS., VairC., ColibroD., LafaceP. and FarrellK., Fast speaker recognition scoring using i-vector posteriors and probabilistic linear discriminant analysis (2016). URL https://www.google.com/patents/US9373330. US Patent 9,373,330
8.
DehakN., Discriminative and generative approaches for longand short-term speaker characteristics modeling: Application to speaker verification, Ecole de Technologie Superieure (Canada) (2009).
9.
DehakN., KennyP., DehakR., DumouchelP. and OuelletP., Front-end factor analysis for speaker verification, Audio, Speech, and Language Processing, IEEE Transactions on19(4) (2011), 788–798. DOI: 10.1109/TASL.2010.2064307
10.
DupuyG., MeignierS., DelégliseP., EsteveY., Recent improvements on ilp-based clustering for broadcast news speaker diarization, In: Proceedings of Odyssey, 2014.
11.
EverittB., LandauS., LeeseM., StahlD., Cluster Analysis. Wiley Series in Probability and Statistics. Wiley, 2011.
12.
GononG., BimbotF. and GribonvalR., Probabilistic scoring using decision trees for fast and scalable speaker recognition, Speech Communication51(11) (2009), 1065–1081. DOI: https://doi.org/10.1016/j.specom.2009.02.007
13.
GreenbergC.S., BanséD., DoddingtonG.R., Garcia-RomeroD., GodfreyJ.J., KinnunenT., MartinA.F., McCreeA., PrzybockiM., ReynoldsD.A., The nist speaker recognition i-vector machine learning challenge, In: Odyssey: The Speaker and Language Recognition Workshop2014. URL http://cs.uef.fi/odyssey2014/program/pdfs/58.pdf
14.
HuY., WuD. and NucciA., Fuzzy-clustering-based decision tree approach for large population speaker identification, Audio, Speech, and Language Processing, IEEE Transactions on21(4) (2013), 762–774. DOI: 10.1109/TASL.2012.2234113
15.
KennyP., BoulianneG., OuelletP. and DumouchelP., Joint factor analysis versus eigenchannels in speaker recognition, Audio, Speech, and Language Processing, IEEE Transactions on15(4) (2007), 1435–1447. DOI: 10.1109/TASL.2006.881693
16.
KhouryE., El ShafeyL., M.Ferras and S.Marcel, Hierarchical speaker clustering methods for the nist i-vector challenge, In: Odyssey: The Speaker and Language Recognition Workshop, EPFL-CONF-198439, 2014.
17.
KinnunenT., KarpovE. and FrantiP., Real-time speaker identification and verification, Speech and Audio Processing, IEEE Transactions on14(1) (2006), 277–288. DOI: 10.1109/TSA.2005.853206
18.
KinnunenT. and LiH., An overview of text-independent speaker recognition: From features to supervectors, Speech Communication52(1) (2010), 12–40. DOI: https://doi.org/10.1016/j.specom.2009.08.009
19.
KumarA., HanmandluM. and GuptaH., Fuzzy binary decision tree for biometric based personal authentication, Neurocomputing99 (2013), 87–97. DOI: https://doi.org/10.1016/j.neucom.2012.06.016
20.
LeskiJ.M. and KotasM., Hierarchical clustering with planar segments as prototypes, Pattern Recognition Letters54 (2015), 1–10. DOI: https://doi.org/10.1016/j.patrec.2014.11.012
21.
LiuG., YuC., MisraA., ShokouhiN., HansenJ.H., Investigating state-of-the-art speaker verification in the case of unlabeled development data, In: Proc Odyssey Speaker and Language Recognition Workshop, Joensuu, Finland, 2014.
22.
LloydS.P., Least squares quantization in pcm, Information Theory, IEEE Transactions on28(2) (1982), 129–137. DOI: 10.1109/TIT.1982.1056489
23.
MaJ., SilovskyJ., SiuM.H., KimballO., Large-scale speaker search using plda on mismatched conditions, In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, pp. 1846–1850 DOI: 10.1109/ICASSP.2015.7178290
24.
MartinA., DoddingtonG., KammT., OrdowskiM., PrzybockiM., The det curve in assessment of detection task performance, Tech Rep, DTIC Document, 1997.
25.
PellomB.L. and HansenJ.H., An efficient scoring algorithm for gaussian mixture model based speaker identification, Signal Processing Letters, IEEE5(11) (1998), 281–284. DOI: 10.1109/97.728467
26.
ReynoldsD.A., Speaker identification and verification using gaussian mixture speaker models, Speech Communication17(1) (1995), 91–108. DOI: https://doi.org/10.1016/0167-6393(95)00009-D
27.
ReynoldsD.A. and RoseR.C., Robust text-independent speaker identification using gaussian mixture speaker models, Speech and Audio Processing, IEEE Transactions on3(1) (1995), 72–83. DOI: 10.1109/89.365379
28.
SarkarA., RathS., UmeshS., Fast approach to speaker identification for large population using mllr and sufficient statistics, Communications (NCC), 2010 National Conference on, IEEE, 2010, pp. 1–5. DOI: 10.1109/NCC.2010.5430206.
29.
SchmidtL., SharifiM., MorenoI.L., Large-scale speaker identification, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, pp. 1650–1654. DOI: 10.1109/ICASSP.2014.6853878
30.
TogneriR. and PullellaD., An overview of speaker identification: Accuracy and robustness issues, Circuits and systems Magazine, IEEE11(2) (2011), 23–61. DOI: 10.1109/MCAS.2011.941079
XiongZ., ZhengT.F., SongZ., SoongF. and WuW., A treebased kernel selection approach to efficient gaussian mixture model– universal background model based speaker identification, Speech Communication48(10) (2006), 1273–1282. DOI: https://doi.org/10.1016/j.specom.2006.06.011
34.
ZeinaliH., SametiH., BabaaliB., A fast speaker identification method using nearest neighbor distance, 2012 IEEE 11th International Conference on Signal Processing, (2012), vol. 3, pp. 2159–2162. DOI: 10.1109/ICoSP.2012.6492008
35.
ZeinaliH., SametiH., HadianH., Real-time speaker identification using speaker model distance, In: 2015 23rd Iranian Conference on Electrical Engineering, 2015, pp. 643–647. DOI: 10.1109/IranianCEE.2015.7146293
