• Home
  • Search
  • Robust speech recognition using compression of Mel sub-band energies and temporal filtering
  • Cite Icon1
  • https://doi.org/10.1109/istel.2010.5734124Copy DOI Icon

Robust speech recognition using compression of Mel sub-band energies and temporal filtering

  • Dec 1, 2010
  • Naghmeh Moradi +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The Mel-frequency cepstral coefficients (MFCC) are commonly used in speech recognition systems. But, they are highly sensitive to presence of external noise. In this paper, we propose a two-step method to compensate noise effects on MFCC. In the first step, we propose a sub-band SNR-dependent compression function for Mel sub-band energies to give higher weights to sub-bands less contaminated with noise and give lower weights to sub-bands more contaminated with noise. In the second step, we apply temporal filters to the weighted MFCCs in order to improve their temporal characteristics. Our results on Aurora2 databases show that the proposed method has higher performance than both of conventional temporal filtering methods and weighted MFCC.

Similar Papers
  • Research Article
  • Citations2

Frequency domain analysis of MFCC feature extraction in children’s speech recognition system

  • Feb 26, 2022
  • JURNAL INFOTEL
  • Risanuri Hidayat
  • Conference Article
  • Citations59

Denoising Speech for MFCC Feature Extraction Using Wavelet Transformation in Speech Recognition System

  • Jul 01, 2018
  • Risanuri Hidayat +3
  • Research Article
  • Citations28

Performance evaluation of Hindi speech recognition system using optimized filterbanks

  • Apr 16, 2018
  • Engineering Science and Technology, an International Journal
  • Mohit Dua +2
  • Research Article
  • Citations7

Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal.

  • Apr 12, 2021
  • Journal of Clinical Sleep Medicine
  • Bochun Wang +6
  • Conference Article
  • Citations3

Significance of acoustic features for designing an emotion classification system

  • Dec 01, 2014
  • Sudhakar Kumar +2
  • Conference Article
  • Citations7

Particle Swarm Optimisation of Mel-frequency Cepstral Coefficients computation for the classification of asphyxiated infant cry

  • Oct 01, 2010
  • A Zabidi +4
  • Research Article
  • Citations28

Speech Recognition of Moroccan Dialect Using Hidden Markov Models

  • Jan 01, 2019
  • Procedia Computer Science
  • Bezoui Mouaz +2
  • Book Chapter
  • Citations1

Hybrid Feature Extraction Technique for Tamil Automatic Speech Recognition System in Noisy Environment

  • Jan 01, 2022
  • S Girirajan +1
  • Book Chapter
  • Citations2

Analysis of Performance Improvement for Speaker Verification by Combining Feature Vectors of LPC Spectral Envelope, MFCC and pLPC Pole Distribution

  • Jan 01, 2022
  • Haruki Shigeta +4
  • Conference Article
  • Citations1

Analysis of Amplitude Threshold on Speech Recognition System

  • Sep 19, 2020
  • 2020 International Seminar on Application for Technology of Information and Communication (iSemantic)
  • Risanuri Hidayat +1
  • Research Article
  • Citations70

Chip design of MFCC extraction for speech recognition

  • Aug 25, 2002
  • Integration
  • Jia-Ching Wang +2
  • Conference Article
  • Citations1

MFCC Extraction Based on F-Ratio and Correlated Distance Criterion in Speaker Recognition

  • Jan 01, 2009
  • Jian-Wei Zhu +3
  • Conference Article

The formant structure based feature parameter for speech recognition

  • May 04, 2004
  • Junhui Zhao +2
  • Conference Article
  • Citations6

Classification of pulmonary crackles and pleural friction rubs using MFCC statistical parameters

  • Sep 01, 2016
  • Sibghatullah I Khan +1
  • Conference Article
  • Citations5

Robust Front-End Based on MVA and HEQ Post-processing for Arabic Speech Recognition Using Hidden Markov Model Toolkit (HTK)

  • Oct 01, 2017
  • Elhem Techini +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.