Abstract
This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training condition and testing condition for the automatic speech recognition (ASR) system, specifically in the car environments. 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 car environment. This paper proposes an efficient spectral subtraction scheme focused to specifically low SNR noisy environments by distinguishing the speech-dominant segment from the noise-dominant segment 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.
Original language | English |
---|---|
Pages (from-to) | 648-651 |
Number of pages | 4 |
Journal | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
Volume | 1 |
Publication status | Published - 2003 |
Event | 2003 IEEE International Conference on Accoustics, Speech, and Signal Processing - Hong Kong, Hong Kong Duration: 2003 Apr 6 → 2003 Apr 10 |
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering