Nonnegative Tensor Factorization-Based Wind Noise Reduction

Jeon KM, Park JH, Yu SW, Lee YH, Cho CS, Kim HK. Nonnegative Tensor Factorization-Based Wind Noise Reduction. In: AES Convention 139. Audio Engineering Society; 2015. Paper 9401. Available from: https://aes.org/publications/elibrary-page/?id=17958

@inproceedings{Jeon2015_17958,
  author = {Jeon, Kwang Myung and Park, Ji Hyun and Yu, Seung Woo and Lee, Young Han and Cho, Choong Sang and Kim, Hong Kook},
  title = {{Nonnegative Tensor Factorization-Based Wind Noise Reduction}},
  booktitle = {AES Convention 139},
  note = {Paper 9401},
  year = {2015},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17958}
}

TY  - CPAPER
TI  - Nonnegative Tensor Factorization-Based Wind Noise Reduction
AU  - Jeon, Kwang Myung
AU  - Park, Ji Hyun
AU  - Yu, Seung Woo
AU  - Lee, Young Han
AU  - Cho, Choong Sang
AU  - Kim, Hong Kook
T2  - AES Convention 139
M1  - Paper 9401
PY  - 2015
DA  - 2015/10/06
UR  - https://aes.org/publications/elibrary-page/?id=17958
PB  - Audio Engineering Society
LA  - en
AB  - In this paper a wind noise reduction method based on nonnegative tensor factorization (NTF) is proposed to enhance the audio quality recorded using an outdoor multichannel microphone array. The proposed method first prepares learned bases for NTF by training exemplar blocks of spectral magnitudes for a series of wind noises and audio contents. Then, the spectral magnitudes of wind noise to be reduced are estimated from the exemplar blocks. Finally, a wind noise reduction multichannel filter is constructed based on a minimum mean squared error (MMSE) criterion and applied to the multichannel noisy signal to obtain the signal with reduced wind noise. The performance of the proposed method is compared with those of conventional methods using minimum statistics (MS) and nonnegative matrix factorization (NMF) for wind noise reduction. As a result, it is shown that the proposed method provides a higher signal-to-distortion ratio (SDR), signal-to-interference ratio (SIR), and signal-to-artifact ratio (SAR) than the conventional methods under various signal-to-noise ratio (SNR) conditions.
ER  -