Dialog Enhancement via Spatio-Level Filtering and Classification

Master AS, Lu L, Lehtonen HM, Mundt H, Purnhagen H, Darcy D. Dialog Enhancement via Spatio-Level Filtering and Classification. In: AES Convention 149. Audio Engineering Society; 2020. Paper 10427. Available from: https://aes.org/publications/elibrary-page/?id=20964

@inproceedings{Master2020_20964,
  author = {Master, Aaron S. and Lu, Lie and Lehtonen, Heidi-Maria and Mundt, Harald and Purnhagen, Heiko and Darcy, Dan},
  title = {{Dialog Enhancement via Spatio-Level Filtering and Classification}},
  booktitle = {AES Convention 149},
  note = {Paper 10427},
  year = {2020},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20964}
}

TY  - CPAPER
TI  - Dialog Enhancement via Spatio-Level Filtering and Classification
AU  - Master, Aaron S.
AU  - Lu, Lie
AU  - Lehtonen, Heidi-Maria
AU  - Mundt, Harald
AU  - Purnhagen, Heiko
AU  - Darcy, Dan
T2  - AES Convention 149
M1  - Paper 10427
PY  - 2020
DA  - 2020/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20964
PB  - Audio Engineering Society
LA  - en
AB  - Dialog enhancement (DE) is a feature that allows a listener to increase the level of dialog in a content item relative to backgrounds. DE is “unguided” if only the finished mix is available, meaning that a DE system must estimate the dialog. Spatio-Level Filtering (SLF) is a source separation technology that, when combined with dialog classification, allows for high-quality unguided DE for typical entertainment content in a stereo or higher channel count format. SLF exploits spatial and level information and requires little lookahead, memory, computation and training data. To evaluate results, we conduct two subjective listening experiments which indicate favorable performance.
ER  -