Abstract
In this paper an automatic speaker recognizer is tested on a speech database with emotional speech. The automatic speaker recognizer is based on mel-frequency cepstral coefficients as features of a speaker and covariance matrices as speaker models. The speaker models are trained on one sentence of neutral speech for each speaker. Other sentences from the same speech database are used for testing, including both neutral and four emotional states: happiness, fear, sadness, and anger. The aim of research is to investigate the impact of acted emotional speech to accuracy of automatic speaker recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Campbell Jr., J.P.: Speaker recognition: a tutorial. Speaker recognition: a tutorial. Proceedings of the IEEE 85(9), 1437–1462 (1997)
Delić, V., Sečujski, M., Jakovljević, N.: Action model of human-machine speech communication. In: Proceedings of the 16th Telecommunications forum TELFOR 2008, Serbia, Belgrade, pp. 680–683 (2008) (in Sebian)
Kinnunen, T., Li, H.: An overview of text-independent speaker recognition: From features to supervectors. Speech Communication 52, 12–40 (2010)
Bimbot, F., Bonastre, J.-F., Fredouille, C., Gravier, G., Magrin-Chagnolleau, I., Meignier, S., Merlin, T., Ortega-Garcia, J., Petrovska-Delacrétaz, D., Reynolds, D.A.: A Tutorial on Text-Independent Speaker Verification. EURASIP Journal on Applied Signal Processing 4, 430–451 (2004)
Jokić, I., Jokić, S., Perić, Z., Gnjatović, M., Delić, V.: Influence of the Number of Principal Components used to the Automatic Speaker Recognition Accuracy. Electronics and Electrical Engineering 7(123), 83–86 (2012)
Jokić, I., Jokić, S., Delić, V., Perić, Z.: Towards a Small Intra-Speaker Variability Models. In: 18th International Conference ELECTRONICS 2014, Palanga, Lithuania, 16th-18th June 2014, Electronics and Electrical Engineering, Kaunas, vol. 20(6), pp. 100–103 (2014)
Raja, G.S., Dandapat, S.: Speaker recognition under stressed condition. International Journal of Speech Technology 13(3), 141–161 (2010)
Devi, J.S., Srinivas, Y., Nandyala, S.P.: Automatic Speech Emotion and Speaker Recognition based on Hybrid GMM and FFBNN. International Journal on Computational Sciences & Applications (IJCSA) 4(1), 35–42 (2014)
Wu, W., Zheng, T.F., Xu, M.-X., Bao, H.-J.: Study on Speaker Verification on Emotional Speech. In: INTERSPEECH 2006 – ICSLP, Pittsburgh, Pennsylvania, September 17-21, pp. 2102–2105 (2006)
Wildermoth, B.R.: Text-Independent Speaker Recognition Using Source Based Features. M. Phil. Thesis, Griffith University, Brisbane, Australia (2001)
Jovičić, S.T., Kašić, Z.: Đorđević, M., Rajković M.: Serbian emotional speech database: design, processing and evaluation. In: Proc. of the SPECOM 2004: 9th Conference Speech and Computer, St. Petersburg, Russia, pp. 77–81 (2004)
Jokić, S., Krčo, S., Sakač, D., Jokić, I., Delić, V.: Autonomic telemedical application for Android based mobile devices. In: Proc. of the 11th Symposium of Neural Network Applications in Electrical Engineering, NEUREL 2012, Beograd, Srbija, pp. 231–234 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Jokić, I., Jokić, S., Delić, V., Perić, Z. (2014). Impact of Emotional Speech to Automatic Speaker Recognition - Experiments on GEES Speech Database. In: Ronzhin, A., Potapova, R., Delic, V. (eds) Speech and Computer. SPECOM 2014. Lecture Notes in Computer Science(), vol 8773. Springer, Cham. https://doi.org/10.1007/978-3-319-11581-8_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-11581-8_33
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11580-1
Online ISBN: 978-3-319-11581-8
eBook Packages: Computer ScienceComputer Science (R0)