Computational Science — ICCS 2003

Volume 2660 of the series Lecture Notes in Computer Science pp 1109-1116


Spectral Subtraction Using Spectral Harmonics for Robust Speech Recognition in Car Environments

  • Jounghoon BehAffiliated withDepartments of Electronics and Computer Engineering, Korea University
  • , Hanseok KoAffiliated withDepartments of Electronics and Computer Engineering, Korea University

* Final gross prices may vary according to local VAT.

Get Access


This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training and testing condition for the automatic speech recognition (ASR) system, specifically in car environment. The conventional spectral subtraction schemes rely on the signal-to-noise ratio (SNR) such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, since these schemes are based on the postulation that the power spectrum of noise is in general at the lower level in magnitude than that of speech. Therefore, while such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. This paper proposes an efficient spectral subtraction scheme focused specifically to low SNR noisy environment by representing harmonics distinctively in speech spectrum. Representative experiments confirm the superior performance of the proposed method over conventional methods. The experiments are conducted using car noise-corrupted utterances of Aurora2 corpus.