Abstract
Speech processing has emerged as one among the most important application areas of digital signal processing. In the present world, the speech processing has become essential for technological developments in various aspects and this technology is also incorporated in many gadgets. Emotion-based recognition is where the emotion of the person is identified from the differences in stress and other properties of speech. The features such as intensity, formants, bandwidth, and pitch vary with the change in emotion. These changes are identified, and the emotion is recognized with respect to the average value in that particular emotion. This project aims to recognize the emotion in Telugu language. The speeches of different speakers are collected for the same sentence in three different emotions (happy, neutral, and bore), and various features are extracted from these collected speeches. Finally, an algorithm is proposed to recognize the emotion based on the features extracted. Its applications are access control, transaction authentication, law enforcement, etc. The recognition accuracy to recognize the emotion of the speaker is 79%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hansen, J.H.L., Varadarajan, V.: Analysis and compensation of Lombard speech across noise type and levels with application to in-set/out-of-set speaker recognition. IEEE Trans. Audio Speech Lang. Process. 17(2) (Feb 2009)
Stolcke, A., Kajarekar, S.S., Ferrer, L., Shrinberg, E.: Speaker recognition with session variability normalization based on MLLR adaptation transforms. IEEE Trans. Audio Speech Lang. Process. 15(7) (Sept 2007)
Eriksson, T., Kim, S., Kang, H.-G., Lee, C.: An information-theoretic perspective on feature selection in speaker recognition. IEEE Signal Process. Lett. 12(7) (July 2005)
Ortega-Garcia, J., Gonzslez-Rodriguez, J., Cruz-Llanas, S.: Speech variability in automatic speaker recognition systems for commercial and forensic purposes. IEEE AES Syst. Mag. (Nov 2000)
Saeed, K., Nammous, M.K.: A speech-and-speaker identification system: feature extraction, description, and classification of speech-signal image. IEEE Trans. Ind. Electron. 54(2), 887–897 (Apr 2007)
Aronowitz, H., Burshtein, D.: Efficient speaker recognition using approximated cross entropy (ACE). IEEE Trans. Audio Speech Lang. Process. 15(7), 2033–2043 (2007)
Besson, P., et al.: Extraction of audio features specific to speech production for multimodal speaker detection. IEEE Trans. Multimed. 10(1), 63–73 (Jan 2008)
Parthasarathi, S.H.K., et al.: Privacy-sensitive audio features for speech/non-speech detection. IEEE Trans. Audio Speech Lang. Process. 19(8), 2538–2551 (Nov 2011)
Dharanipragada, S., et al.: Robust feature extraction for continuous speech recognition using the MVDR spectrum estimation method. IEEE Trans. Audio Speech Lang. Process. 15(1), 224–234 (Jan 2007)
Wu, Q., et al.: Robust multifactor speech feature extraction based on Gabor analysis. IEEE Trans. Audio Speech Lang. Process. 19(4), 927–936 (May 2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mannepalli, K., Sastry, P.N., Suman, M. (2018). Analysis of Emotion Recognition System for Telugu Using Prosodic and Formant Features. In: Agrawal, S., Devi, A., Wason, R., Bansal, P. (eds) Speech and Language Processing for Human-Machine Communications. Advances in Intelligent Systems and Computing, vol 664. Springer, Singapore. https://doi.org/10.1007/978-981-10-6626-9_15
Download citation
DOI: https://doi.org/10.1007/978-981-10-6626-9_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6625-2
Online ISBN: 978-981-10-6626-9
eBook Packages: EngineeringEngineering (R0)