Yifeng Wang

Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

By explicitly modeling spectral channel variations and inter-channel similarity, SPDDA overcomes the realism-diversity tradeoff in hyperspectral data augmentation, achieving state-of-the-art domain generalization performance.