# Towards Listening to 10 People Simultaneously: An Efficient Permutation Invariant Training of Audio Source Separation Using Sinkhorn’s Algorithm

> Research article (ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021) · cited 10× · AI/ML

**Wikidata**: [openalex:W3094380169](https://www.wikidata.org/wiki/openalex:W3094380169)  
**Source**: https://4ort.xyz/entity/towards-listening-to-10-people-simultaneously-an-efficient-permutation-invariant-training-of-audio-source-separation-usi