A Novel Embedded Speaker Verification on System on Chip

Pengfei Mao; Jia Liu

doi:10.1109/FSKD.2009.714

Fuzzy Systems and Knowledge Discovery, Fourth International Conference on

A Novel Embedded Speaker Verification on System on Chip

Year: 2009, Volume: 5, Pages: 481-484

DOI Bookmark: 10.1109/FSKD.2009.714

Authors

Pengfei Mao
Jia Liu

Abstract

This paper realizes a Text-Independent, Speaker Verification system on a System on Chip (SOC) platform. The system uses Mel-Frequency Cepstral Coefficients (MFCC) features with a Gaussian Mixture Model-Universal Background Model ( GMM-UBM ) speaker model. To deal with resource limitations, a new speaker-centric score normalization technique is introduced. This normalization technique results in a relative EER reduction of 44.9% compared to no normalization.

Like what you’re reading?

Already a member?

Get this article FREE with a new membership!

Robust Speaker Verification Using a New Front End Based on Multitaper and Gammatone Filters
2014 Tenth International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)
Improved accuracy of speaker verification system in noisy environment
2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)
Discrete Fractional Fourier Transform and Vector Quantization Based Speaker Identification System
2014 Fourth International Conference on Advanced Computing & Communication Technologies (ACCT)
Effect of MFCC normalization on vector quantization based speaker identification
2010 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2010)
A Comparative Study in Emotional Speaker Recognition in Noisy Environment
2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA)
Very low complexity prompted speaker verification system based on HMM-modeling
Proceedings of International Conference on Acoustics, Speech and Signal Processing (CASSP'02)
Robust speaker verification using GFCC and joint factor analysis
2014 5th International Conference on Computing, Communication and Networking Technologies (ICCCNT)
Speaker Recognition Based on Weighted Mel-cepstrum
Convergence Information Technology, International Conference on
Real time speaker recognition of letter ‘zha’ in Tamil language
2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT)
Improving Speaker Verification Robustness by Front-End Diversity and Score Level Fusion
2013 International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)

A Novel Embedded Speaker Verification on System on Chip

Authors

Abstract

Related Articles