Title :
Audio noise suppression based on neuromorphic saliency and phoneme adaptive filtering [speech enhancement]
Author :
Hu, Rongqiang ; Anderson, David V.
Author_Institution :
Center for Signal & Image Process., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
An acoustic noise suppression algorithm is described that uses perceptually inspired signal detection techniques to estimate the presence of speech cues in the presence of low SNRs. The signal detector generates frequency-dependent soft-decisions that are used in determining speech presence and in controlling parameters for the speech enhancement gains. With the input of speech segmentation, a phoneme adaptive mechanism is introduced to enhance speech by moderate state-dependent filtering.
Keywords :
adaptive filters; band-pass filters; interference suppression; signal denoising; speech enhancement; acoustic noise suppression; audio noise suppression; frequency-dependent soft-decisions; neuromorphic saliency; passband analysis filter bank; perceptually inspired signal detection techniques; phoneme adaptive filtering; speech cue presence estimation; speech segmentation; speech spectrogram; state-dependent filtering; Acoustic noise; Adaptive filters; Background noise; Bandwidth; Detectors; Filter bank; Neuromorphics; Signal detection; Signal processing; Speech enhancement;
Conference_Titel :
Digital Signal Processing Workshop, 2004 and the 3rd IEEE Signal Processing Education Workshop. 2004 IEEE 11th
Print_ISBN :
0-7803-8434-2
DOI :
10.1109/DSPWS.2004.1437976
