INTERSPEECH 2004 - ICSLP
This paper presents robust speech enhancement using noise estimation based on smoothing of spectral noise floor (SNF) for nonstationary noise environments. The spectral gain function is obtained by well-known log-spectral amplitude (LSA) estimation criterion associated with the speech presence uncertainty. The noise estimate is given by averaging actual spectral power values, using a smoothing parameter that depends on smoothing of spectral noise floor. The noise estimator is very simple but achieves a good tracking capability for a nonstationary noise. Its enhanced speech is free of musical tones and reverberation artifacts and sounds very natural compared to methods using other short-time spectrum attenuation techniques. The performance is measured by the segmental signal-to-noise ratio (SNR), the speech/ speaker recognition accuracy and the speaker change detection rate for the audio segmentation using MFCC-features (Mel-scale Frequency Cepstral Coefficients) in comparison to other single microphone noise reduction methods.
Bibliographic reference. Kim, Hyoung-Gook / Sikora, Thomas (2004): "Speech enhancement based on smoothing of spectral noise floor", In INTERSPEECH-2004, 2701-2704.