Speech Activity Detection and its Evaluation in Speaker Diarization System
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2017, Vol 16, Issue 1
Abstract
In speaker diarization, the speech/voice activity detection is performed to separate speech, non-speech and silent frames. Zero crossing rate and root mean square value of frames of audio clips has been used to select training data for silent, speech and nonspeech models. The trained models are used by two classifiers, Gaussian mixture model (GMM) and Artificial neural network (ANN), to classify the speech and non-speech frames of audio clip. The results of ANN and GMM classifier are compared by Receiver operating characteristics (ROC) curve and Detection ErrorTradeoff (DET) graph. It is concluded that neural network based SADcomparatively better than Gaussian mixture model based SAD.
Authors and Affiliations
Sukhvinder Kaur, J. S. Sohal
Keywords
Related Articles
- EP ID EP650926
- DOI 10.24297/ijct.v16i1.5893
- Views 80
- Downloads 0
A new approach to Computer-Based Examinations using word documents and spreadsheets
This paper describes a new approach to computer based testing where lecturers submit questions via word document which is processed to produce an examination, with student results analyzed and reported in a spreadsheet....
VARIABLE GRAVITY FIELD AND THROUGHFLOW EFFECTS ON PENETRATIVE CONVECTION IN A POROUS LAYER
The effect of vertical throughflow and variable gravity field on the onset of penetrative convection simulated via internal heating in a porous medium is studied. Flow in the porous medium is governed by Forchheimer-exte...
Printed Arabic Characters Classification using A Statistical Approach
In this paper, we propose simple classifiers for printed Arabic characters based on statistical analysis. 109 printed Arabic character images are created for each one of transparent, simplified and traditional Arabic fon...
Load-Balancing using HA Proxy on Multipath System with Flow Slice
To provide switching capacity in terabit or petabit uses core routers in multipath switching systems (MPS). Without disturbing the order of intra flow packets, the load balance across multiple paths is the main issue of...
Improvised Admissible Kernel Function for Support Vector Machines in Banach Space for Multiclass Data
Classification based on supervised learning theory is one of the most significant tasks frequently accomplished by so-called Intelligent Systems. Contrary to the traditional classification techniques that are used to val...