Source Feature Based Gender Identification System Using GMM
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 2
Abstract
In this paper, through different experimental studies it is demonstrated that the excitation component of speech can be exploited for text independent gender identification system. Linear prediction (LP) residual is used as a representation of excitation information in speech. The speakerspecific information in the excitation of voiced speech is captured using Gaussian Mixture Model (GMM). The decrease in the error during training and recognizing correct gender during testing demonstrates that the excitation component of speech contains speaker-specific information and is indeed being captured by GMM. It is demonstrated that the proposed gender identification system using excitation information requires significantly less amount of data both during training as well as in testing, compared to the other gender identification systems. A gender identification study using source feature for different Mixtures Components, train and test duration has been exploited. We demonstrate the gender identification studies on TIMIT database.
Authors and Affiliations
R. RAJESHWARA RAO , NAGESH
Keywords
Related Articles
- EP ID EP124266
- DOI -
- Views 108
- Downloads 0
Cooperative Communications: A New Trend in the Wireless World
This Wireless channel while offering independence of movement also introduces un-reliability in the messages received at the destination. Various strategies have been introduced so far to mitigate the effects of the chan...
Analysis of AODV Routing Protocol for Minimized Routing Delay in Ad Hoc Networks
Ad hoc wireless networks consists of mobile terminals communicating directly with other mobile terminals without any pre existing infrastructure. In Ad hoc network each mobile terminal acts as a router to enable multi ho...
Power Control Algorithm for Wireless Sensor Networks using N-Policy M/M/1 Queueing Model
A critical issue in wireless sensor networks is the limited vailability of power and hence optimizing power is very important. In any sensor node, transitions from idle to busy state and vice versa consume most of the po...
Power Control Technique for Efficient Call Admission Control in Advanced Wirless Networks
In 4G networks, call admission control techniques have been proposed to provide Quality of Service (QoS) in a network by restricting the access to network resources. Power control is essential in call admission control i...
Wireless Control LEGO NXT robot using voice commands
This paper presents a wireless interface to control a LEGO NXT robot using voice commands through a computer. To perform speech recognition is used CSLU TOOLKIT with a corpus of Mexican Spanish voice, recognized commands...