Detection of the Effect of Window Duration in an audio Source Separation Paradigm

Miller R, Bulla W, Tarr E. Detection of the Effect of Window Duration in an audio Source Separation Paradigm. In: AES Convention 147. Audio Engineering Society; 2019. Paper 10252. Available from: https://aes.org/publications/elibrary-page/?id=20625

@inproceedings{Miller2019_20625,
  author = {Miller, Ryan and Bulla, Wesley and Tarr, Eric},
  title = {{Detection of the Effect of Window Duration in an audio Source Separation Paradigm}},
  booktitle = {AES Convention 147},
  note = {Paper 10252},
  year = {2019},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20625}
}

TY  - CPAPER
TI  - Detection of the Effect of Window Duration in an audio Source Separation Paradigm
AU  - Miller, Ryan
AU  - Bulla, Wesley
AU  - Tarr, Eric
T2  - AES Convention 147
M1  - Paper 10252
PY  - 2019
DA  - 2019/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20625
PB  - Audio Engineering Society
LA  - en
AB  - Non-negative matrix factorization (NMF) is a commonly used method for audio source separation in applications such as polyphonic music separation and noise removal. Previous research evaluated the use of additional algorithmic components and systems in efforts to improve the effectiveness of NMF. This study examined how the short-time Fourier transform (STFT) window duration used in the algorithm might affect detectable differences in separation performance. An ABX listening test compared speech extracted from two types of noise-contaminated mixtures at different window durations to determine if listeners could discriminate between them. It was found that the window duration had a significant impact on subject performance in both white- and conversation-noise cases with lower scores for the latter condition.
ER  -