Abstract
Singer Identification (SID) is one of the major interests in the field of Music Information Retrieval (MIR). The researches in SID in the last decade have been primarily focused in improving the identification accuracy by using better features in addition to Mel-frequency Cepstral Coefficients (MFCC). This work primarily attempts to explore a time-domain feature from the model parameters of the time-series Auto-regressive-Moving Average (ARMA) model to be used as one of the features for SID. The ARMA features are also combined along with MFCC to compare the results and observe its performance in SID. The MFCC and ARMA features are trained and classified using the Gaussian Mixture Model (GMM). Most of the literature deals in the spectral domain for feature extraction. Therefore, this paper mainly seeks to find the scope of using time-domain model parameters as one of the features in decision-making problems in the field of MIR.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bartsch MA, Wakefield GH (2004) Singing voice identification using spectral envelope estimation. IEEE Trans Speech Audio Process 12(2):100–109. https://doi.org/10.1109/TSA.2003.822637
Cai W, Li Q, Guan X (2011) Automatic singer identification based on auditory features. In: 2011 seventh international conference on natural computation, vol 3, pp 1624–1628. https://doi.org/10.1109/ICNC.2011.6022500
Deshmukh S (2014) North indian classical musics singer identification by timbre recognition using mir toolbox. Int J Comput Appl 91(4):1–4
Devaney J (2016) Inter-versus intra-singer similarity and variation in vocal performances. Int J Comput Appl 45(3):252–264. https://doi.org/10.1080/09298215.2016.1205631
Johnson AM, Kempster GB (2011) Classification of the classical male singing voice using long-term average spectrum. J Voice 25(5):538–543. https://doi.org/10.1016/j.jvoice.2010.05.009, http://www.sciencedirect.com/science/article/pii/S089219971000130X
Kim YE, Whitman, B (2002) Singer identification in popular music recordings using voice coding features. In: Proceedings of the 3rd international conference on music information retrieval, pp 164–169
Nwe TL, Li H (2007) Exploring vibrato-motivated acoustic features for singer identification. IEEE Trans Audio Speech Lang Process 15(2):519–530. https://doi.org/10.1109/TASL.2006.876756
Patil HA, Radadia PG, Basu TK (2012) Combining evidences from Mel cepstral features and cepstral mean subtracted features for singer identification. In: 2012 international conference on Asian language processing, pp 145–148. https://doi.org/10.1109/IALP.2012.33
Tsai WH, Wang HM (2006) Automatic singer recognition of popular music recordings via estimation and modeling of solo vocal signals. IEEE Trans Audio Speech Lang Process 14(1):330–341. https://doi.org/10.1109/TSA.2005.854091
Zhang T (2003) Automatic singer identification. In: Proceedings of the 2003 international conference on multimedia and expo, ICME ’03, vol 2, pp 33–36. IEEE Computer Society, Washington, DC. http://dl.acm.org/citation.cfm?id=1170745.1171614
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bonjyotsna, A., Bhuyan, M. (2020). Singer Identification Using Time-Series Auto-Regressive Moving Average. In: Kadambi, G., Kumar, P., Palade, V. (eds) Emerging Trends in Photonics, Signal Processing and Communication Engineering. Lecture Notes in Electrical Engineering, vol 649. Springer, Singapore. https://doi.org/10.1007/978-981-15-3477-5_27
Download citation
DOI: https://doi.org/10.1007/978-981-15-3477-5_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3476-8
Online ISBN: 978-981-15-3477-5
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)