Loading...

Automatic noise recognition based on neural network using LPC and MFCC feature parameters

Haghmaram, R ; Sharif University of Technology | 2012

682 Viewed
  1. Type of Document: Article
  2. Publisher: 2012
  3. Abstract:
  4. This paper studies the automatic noise recognition problem based on RBF and MLP neural networks classifiers using linear predictive and Mel-frequency cepstral coefficients (LPC and MFCC). We first briefly review the architecture of each network as automatic noise recognition (ANR) approach, then, compare them to each other and investigate factors and criteria that influence final recognition performance. The proposed networks are evaluated on 15 stationary and non-stationary types of noises with frame length of 20 ms in term of correct classification rate. The results demonstrate that the MLP network using LPCs is a precise ANR with accuracy rate of 99.9%, while the RBF network with MFCCs coefficients goes afterward with 99.0% of accuracy
  5. Keywords:
  6. Accuracy rate ; Classification rates ; Feature parameters ; Frame length ; Mel-frequency cepstral coefficients ; MLP neural networks ; Nonstationary ; Problem-based ; Recognition performance ; Computer science ; Information systems ; Radial basis function networks ; Speech recognition
  7. Source: 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012, 9 September 2012 through 12 September 2012 ; 2012 , Pages 69-73 ; 9781467307086 (ISBN)
  8. URL: http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=6354316&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6354316