Speech Enhancement of Noisy Speech Using Log-Spectral Amplitude Estimator and Harmonic Tunneling
Hyoung‐Gook Kim, Markus Schwab, Nicolas Moreau, Thomas Sikora · 2003
In this paper we present a two stage noise reduction algorithm for speech enhancement. The speech noise removal algorithm is based on a two stage noise filtering LSAHT by log spectral amplitude speech estimator (LSA) and harmonic tunneling (HT) with spectral subtraction. The performance of the system is measured by the segmental signal-to-noise ratio, mean opinion score (MOS) tests, and the recognition accuracy of an Automatic Speech Recognition (ASR) in comparison to other noise reduction methods. 1.