An information set-based robust text-independent speaker authentication
- 7 Downloads
This paper presents a method for the extraction of twofold information set (TFIS) features for the text-independent speaker recognition. The method takes the Mel frequency cepstral coefficients from the frames of a sample speech signal and forms a matrix. From this, both spatial and temporal information components are derived based on the information set concept using the entropy framework. The TFIS features comprising their combination of two components are less in number thus reducing the computational time, complexity and improving the performance under the noisy environment. The proposed approach is tested on three datasets namely NIST-2003, VoxForge 2014 speech corpus and VCTK speech corpus in terms of speed, computational complexity, memory requirement and accuracy. Its performance is validated under different noisy environments at different signal-to-noise ratios.
KeywordsText-independent speaker recognition Information set theory Twofold information set features
This is a part of the ongoing project on “Personal Authentication using Multimodal Behavioral Biometrics: Voice and Gait” and the authors express their gratitude to the Department of Science and Technology, Government of India (Grant No. SB/S3/EECE/0127/2013) for funding the project.
Compliance with ethical standards
Conflict of interest
The authors’ declare that they have no conflict of interest.
Human and animals rights
This article does not contain any studies with direct human participants or animals performed by any of the authors.
- Jawarkar NP, Holambe RS, Basu TK (2011) Use of fuzzy min–max neural network for speaker identification. In: 2011 international conference on recent trends in information technology (ICRTIT)Google Scholar
- Kinnunen T, Hautamäki V, Fränti P (2006) On the use of long-term average spectrum in automatic speaker recognition. In: 5th international symposium on chinese spoken language processing (ISCSLP’06). Singapore, pp 559–567Google Scholar
- Kumar K, Kim C, Stern RM (2011) Delta-spectral cepstral coefficients for robust speech recognition. In: IEEE international conference on acoustics, speech and signal processing (ICASSP)Google Scholar
- Mandasari MI, Mitchell ML, van Leeuwen DA (2011) Evaluation of i-vector speaker recognition systems for forensic application. In: INTERSPEECHGoogle Scholar
- [Online] (2003) The NIST year 2003 speaker recognition evaluation plan. http://www.itl.nist.gov/iad/mig/tests/sre/2003/2003-spkrec-evalplan-v2.2.pdf
- [Online] (2009) The Centre for Speech Technology Research VCTK CorpusGoogle Scholar
- [Online] (2015) VoxForge speech corpus. http://www.repository.voxforge1.org/downloads/SpeechCorpus/Trunk/Audio/Main/
- Pelecanos J, Sridharan S (2001) Feature warping for robust speaker verification. A speaker odyssey—the speaker recognition workshop. Crete, Greece, International Speech Communication Association (ISCA), pp 213–218Google Scholar
- Pinheiro HNB, Vieira SRF, Ren TI, Cavalcanti GDC, de Mattos NPSG (2016). Type-2 fuzzy GMM for text-independent speaker verification under unseen noise conditions. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP)Google Scholar
- Pujol P, Macho D, Nadeu C (2006). On real-time mean-and-variance normalization of speech recognition features. In: 2006 IEEE international conference on acoustics speech and signal processing proceedingsGoogle Scholar
- Wang Y, Liu X, Xing Y, Li M (2008) A novel reduction method for text-independent speaker identification. In: 2008 fourth international conference on natural computationGoogle Scholar
- Zhao X, Wang DL (2013). Analyzing noise robustness of MFCC and GFCC features in speaker identification. In: IEEE international conference on acoustics, speech and signal processing (ICASSP)Google Scholar
- Yuan ZX, Yu CZ, Fang Y (1993) Text independent speaker identification using fuzzy mathematical algorithm. In: IEEE international conference on acoustics, speech, and signal processing, ICASSPGoogle Scholar