A Novel Approach in Text-Independent Speaker Recognition in Noisy Environment
Journal Title: روش های هوشمند در صنعت برق - Year 2014, Vol 5, Issue 19
Abstract
In this paper, robust text-independent speaker recognition is taken into consideration. The proposed method performs on manual silence-removed utterances that are segmented into smaller speech units containing few phones and at least one vowel. The segments are basic units for long-term feature extraction. Sub-band entropy is directly extracted in each segment. A robust vowel detection method is then applied on each segment to separate a high energy vowel that is used as unit for pitch frequency and formant extraction. By applying a clustering technique, extracted short-term features namely MFCC coefficients are combined with long term features. Experiments using MLP classifier show that the average speaker accuracy recognition rate is 97.33% for clean speech and 61.33% in noisy environment for -2db SNR, that shows improvement compared to other conventional methods.
Authors and Affiliations
Nona Heydari Esfahani, Hamid Mahmoodian
Keywords
Related Articles
- EP ID EP328485
- DOI -
- Views 103
- Downloads 0
Design and Implementation of an Optimal PV Refrigeration System in the Smart Grid Considering Multi-objective Optimization
Today, optimization in power systems is an unavoidable necessity. Energy intensity reduction in electrical devices and enhancement of their efficiency and performance, electricity loss reduction and voltage profile impro...
A Duble Quasi-sinusidal Waveform Elicitation From Matrix Converter Based on Orthogonal Strategy
this paper has scrutinized an effective approach regarding to how to elicit double quasi-sinusoidal waveform with orthogonal angles that can be applicable for two-phase induction motors. Hither, to be more precisely decl...
Self-tuning Fuzzy PID Controller for Load Frequency Control in AC Micro-grid with Considering of Input Delay
A micro grid (MG) system that benefits from distributed generation (DG) resources has a non-linear and time-varying nature which encounters the control problem with some difficulties. Also, due to the fact that in the mo...
Power management of a wind energy conversion system equipped by DFIG
Today wind is one of the attractive points of energy area which has got the noticeable amount of investment and studies in this field. Considering the importance of the wind energy and its potentials as one of the renewa...
Evaluation of Starting Current of Induction Motors Using Artificial Neural Network
Induction motors (IMs) are widely used in industry including it be an electrical or not. However during starting period, their starting currents are so large that can damage equipment. Therefore, this current should be e...