IMPROVED DESIGN OF DTW AND GMM CASCADED ARABIC SPEAKER
Abstract: In this paper, we
discuss about the design, implementation and assessment of a two-stage Arabic
speaker recognition system, which aims to recognize a target Arabic speaker
among several people. The first stage uses improved DTW (Dynamic Time Warping)
algorithm and the second stage uses SA-KM-based GMM (Gaussian Mixture Model).
MFCC (Mel Frequency Cepstral Coefficients) and its differences form, as
acoustic feature, are extracted from the sample speeches. DTW provides three
most possible speakers and then the recognition results are conveyed to GMM
training processes. A specified similarity assessment algorithm, KL distance,
is applied to find the best match with the target speaker. Experimental results
show that text-independent recognition rate of the cascaded system reaches 90
percent.
Author: Shuoshuo Chen, Junbo
Zhao, Ruiqi Yang
Journal Code: jptkomputergg130011
Artikel Terkait :
Jp Teknik Komputer gg 2013
- Gamelan Music Onset Detection based on Spectral Features
- Streamed Sampling on Dynamic data as Support for Classification Model
- A Mobile Ecotourism Recommendations System Using Cars-Context Aware Approaches
- Improved Harmony Search Algorithm with Chaos for Absolute Value Equation
- Future Smart Cooking Machine System Design
- A Review of Communication Protocols for Intelligent Remote Terminal Unit Development
- Power Balance AODV Algorithm of WSN in Agriculture Monitoring
- Circularly Polarized Proximity-Fed Microstrip Array Antenna for Micro Satellite
- Ovarian Cancer Identification using One-Pass Clustering and k-Nearest Neighbors
- Localizing Region-Based Level-set Contouring for Common Carotid Artery in Ultrasonography
- Separability Filter for Localizing Abnormal Pupil: Identification of Input Image
- Feature Extraction of Composite Damage on Acoustic Emission Signals
- A Camera Self-Calibration Method Based on Plane Lattice and Orthogonality
- Application of Wavelet Analysis in Detecting Runway Foreign Object Debris
- Palmprint Verification Using Time Series Method
- Time Series Based for Online Signature Verification
- Two-phase Flow Visualization Employing Gauss-Newton Method in Microchannel
- Study on Thermal Conductivity Methane Sensor Constant Temperature Detection Method
- Fuzzy Adaptive PID Control of a New Hydraulic Erecting Mechanism
- Optimization of Membership Functions for the Fuzzy Controllers of the Water Tank and Inverted Pendulum with Differents PSO Variants
- Study of an Improved Fuzzy Direct Torque Control of Induction Motor
- Research of NiMH Battery Modeling and Simulation Based on Linear Regression Analysis Method
- Design and Modeling of an Integrated Micro-Transformer in a Flyback Converter
- Renewable Distributed Generation Models in Three-Phase Load Flow Analysis for Smart Grid
- A Design Study of Dual-Stator Permanent Magnet Brushless DC Motor