Noise Spectrum Estimation Using Line Spectral Frequencies for Robust Speech Recognition
Cited 0 times inCited 0 times in
- Noise Spectrum Estimation Using Line Spectral Frequencies for Robust Speech Recognition
- Jang, Gil-Jin; Park, Jeong-Sik; Kim, Sang-Hun
- Line spectral frequencies (LSF); Noise suppression; Speech recognition
- Issue Date
- 한국음향학회지 , v.31, no.3, pp.179 - 187
- This paper presents a novel method for estimating reliable noise spectral magnitude for acoustic background noise suppression where only a single microphone recording is available. The proposed method finds noise estimates from spectral magnitudes measured at line spectral frequencies (LSFs), under the observation that adjacent LSFs are near the peak frequencies and isolated LSFs are close to the relatively flattened valleys of LPC spectra. The parameters used in the proposed method are LPC coefficients, their corresponding LSFs, and the gain of LPC residual signals, so it suits well to LPC-based speech coders.
Appears in Collections:
- ECE_Journal Papers
can give you direct access to the published full text of this article. (UNISTARs only)
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.