{"id":1806,"date":"2018-07-13T13:52:52","date_gmt":"2018-07-13T10:52:52","guid":{"rendered":"http:\/\/www.eng.biu.ac.il\/gannot\/?page_id=1806"},"modified":"2018-08-19T19:45:52","modified_gmt":"2018-08-19T16:45:52","slug":"source-counting-and-separation-based-on-simplex-analysis","status":"publish","type":"page","link":"https:\/\/www.eng.biu.ac.il\/gannot\/speech-enhancement\/source-counting-and-separation-based-on-simplex-analysis\/","title":{"rendered":"Source counting and separation based on simplex analysis"},"content":{"rendered":"

Bracha Laufer-Goldshtein, Ronen Talmon and Sharon Gannot, \"Source counting and separation based on simplex analysis,\" submitted to IEEE Transactions on Signal Processing, 2018.<\/p>\n

In our experimental study, we consider both simulated data and real-life recordings:<\/p>\n

    \n
  1. Simulation: Clean speech signals (from the TIMIT database) were convolved with room impulse responses from the RIR database [1] recorded in the acoustic lab at Bar-Ilan University, with reverberation time set to 360ms.<\/li>\n
  2. Real-life Experiment: Real recordings of real-life speakers were carried out in a low echoic noisy enclosure as described in [2].<\/li>\n<\/ol>\n

    Simulation<\/u>:<\/strong><\/p>\n

     <\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
    J<\/strong><\/td>\nMixture\u00a0<\/strong><\/td>\nSpeaker 1<\/strong><\/td>\nSpeaker 2<\/strong><\/td>\nSpeaker 3<\/strong><\/td>\nSpeaker 4<\/strong><\/td>\n<\/tr>\n
    2<\/td>\n\n<\/td>\n<\/td>\n<\/tr>\n
    2<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
    2<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
    2<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
    2<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
    2<\/td>\n<\/td>\n<\/td>\n<\/tr>\n
    3<\/td>\n<\/td>\n<\/tr>\n
    3<\/td>\n<\/td>\n<\/tr>\n
    3<\/td>\n<\/td>\n<\/tr>\n
    4<\/td>\n
    4<\/td>\n
    4<\/td>\n