A lowdistortion noise canceller with a novel stepsize control and conditional cancellation. Sugiyama, A. & Miyaharay, R. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 1262-1266, Sep., 2014.
abstract   bibtex   
This paper proposes a low-distortion noise canceller with a novel stepsize control and conditional cancellation. The coefficient adaptation stepsize is controlled by an estimated signal-to-noise ratio (SNR) at the primary input and a relative coefficient magnitude normalized by the reference power. The SNR is estimated based on the noise replica and the output, and converted to a stepsize by an exponential function. This stepsize provides robustness to interference by the desired speech. Conditional cancellation guarantees that the noisy signal power is reduced by noise-replica subtraction. Comparison of the proposed noise canceller with five popular state-of-the-art commercial smartphones demonstrates good enhanced-signal quality with as much as 0.6 PESQ improvement.
@InProceedings{6952432,
  author = {A. Sugiyama and R. Miyaharay},
  booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
  title = {A lowdistortion noise canceller with a novel stepsize control and conditional cancellation},
  year = {2014},
  pages = {1262-1266},
  abstract = {This paper proposes a low-distortion noise canceller with a novel stepsize control and conditional cancellation. The coefficient adaptation stepsize is controlled by an estimated signal-to-noise ratio (SNR) at the primary input and a relative coefficient magnitude normalized by the reference power. The SNR is estimated based on the noise replica and the output, and converted to a stepsize by an exponential function. This stepsize provides robustness to interference by the desired speech. Conditional cancellation guarantees that the noisy signal power is reduced by noise-replica subtraction. Comparison of the proposed noise canceller with five popular state-of-the-art commercial smartphones demonstrates good enhanced-signal quality with as much as 0.6 PESQ improvement.},
  keywords = {adaptive filters;interference suppression;smart phones;speech enhancement;PESQ improvement;signal quality;smartphones;noise-replica subtraction;noisy signal power;exponential function;reference power;coefficient magnitude;SNR;signal-to-noise ratio;coefficient adaptation stepsize;conditional cancellation;stepsize control;low-distortion noise canceller;Speech;Noise cancellation;Signal to noise ratio;Microphones;Speech enhancement;Smart phones;Two microphone;Dual microphone;Low distortion;Noise canceller;Stepsize control},
  issn = {2076-1465},
  month = {Sep.},
}

Downloads: 0