Ambience Separation from Mono Recordings Using Non-Negative Matrix Factorization

Uhle C, Walther A, Hellmuth O, Herre J. Ambience Separation from Mono Recordings Using Non-Negative Matrix Factorization. In: AES Conference: 30th International Conference: Intelligent Audio Environments. Audio Engineering Society; 2007. Paper 17. Available from: https://aes.org/publications/elibrary-page/?id=13915

@inproceedings{Uhle2007_13915,
  author = {Uhle, Christian and Walther, Andreas and Hellmuth, Oliver and Herre, Juergen},
  title = {{Ambience Separation from Mono Recordings Using Non-Negative Matrix Factorization}},
  booktitle = {AES Conference: 30th International Conference: Intelligent Audio Environments},
  note = {Paper 17},
  year = {2007},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=13915}
}

TY  - CPAPER
TI  - Ambience Separation from Mono Recordings Using Non-Negative Matrix Factorization
AU  - Uhle, Christian
AU  - Walther, Andreas
AU  - Hellmuth, Oliver
AU  - Herre, Juergen
T2  - AES Conference: 30th International Conference: Intelligent Audio Environments
M1  - Paper 17
PY  - 2007
DA  - 2007/03/06
UR  - https://aes.org/publications/elibrary-page/?id=13915
PB  - Audio Engineering Society
LA  - en
AB  - This article describes an approach to the problem of upmixing one-channel audio signals for multi-channel reproduction. The proposed method separates an ambient signal from an audio signal by computing the difference between the audio signal and a suitable approximation of the audio signal in the time-frequency domain. The approximation is derived by means of Non-negative Matrix Factorization minimizing the Kullback-Leibler divergence. A surround audio signal is generated by feeding the separated ambient signal into the rear channels. Results of extensive listening tests confirm the listeners' preference of the upmixed audio compared to unprocessed audio and competing upmix algorithms when played back on a 5.0 system.
ER  -