[ICSLP04] Separation of Multiple Concurrent Speeches Using Audio-Visual Speaker Localization and Minimum Variance Beam-forming

Changkyu Choi, Donggeon Kong, Sang Min Yoon, Hyoung-Ki Lee, "Separation of Multiple Concurrent Speeches Using Audio-Visual Speaker Localization and Minimum Variance Beam-forming," in proceedings of International Conference on Spoken Language Processing, October 4-8, 2004, Jeju, KOREA.

[Eight-channel simultaneous recordings of the mixed source signals and music.]
[Three separated speeches by the proposed method.]

[Three separated speeches are further enhanced by the adaptive cross-channel interference canceler (ACCIC).]