Center Extraction GAN

Singh A, Panwar S, Meena N, Srivastava H. Center Extraction GAN. In: Convention Paper. Audio Engineering Society; 2026. Paper 10304. Available from: https://aes.org/publications/elibrary-page/?id=23197

@inproceedings{Singh2026_23197,
  author = {Singh, Avinash and Panwar, Sumit and Meena, Natasha and Srivastava, Hemanshu},
  title = {{Center Extraction GAN}},
  note = {Paper 10304},
  year = {2026},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23197}
}

TY  - CPAPER
TI  - Center Extraction GAN
AU  - Singh, Avinash
AU  - Panwar, Sumit
AU  - Meena, Natasha
AU  - Srivastava, Hemanshu
M1  - Paper 10304
PY  - 2026
DA  - 2026/05/28
UR  - https://aes.org/publications/elibrary-page/?id=23197
PB  - Audio Engineering Society
LA  - en
AB  - Most music content available today is in stereo format, which provides a directional experience to the listener to a certain extent. However, this experience can be further enhanced to improve spatial listening and provide listeners with a more immersive and engaging musical experience. Insufficient separation between instruments can lead to an unbalanced mix, where certain elements dominate others and disrupt the overall harmony. Additionally, instruments may appear flat and confined to a narrow area, reducing the sense of dimensionality in the mix. While stereo audio offers spatial information to some degree, it can be further adapted to transport the listener into an immersive sonic environment. This research presents a novel approach for converting stereo audio into a personalized immersive orchestra like experience by leveraging object-based audio rendering, the listener's sound stage, and surround speaker capabilities. The proposed system separates audio signals into individual objects (such as instruments or vocals) and dynamically maps these objects to specific speakers based on personalized preferences and spatial configurations. This method improves audio localization and enhances the listener's engagement by delivering a tailored auditory experience.
ER  -