ProjectsProject Details

Speaker Diarization Using Dimension Reduction

Project ID: 3084-1-16 ; 2742-2-15
Year: 2016
Student/s: Lee Twito, Ori Shahar
Supervisor/s: Nurit Spingarn

Diarization problem is well known problem in the world of speech recognition and speech processing. Our project goal is Speaker diarization in recorded conversation. We try a new approach for solving this problem, using dimension reduction algorithm (LLE). The results are compared to a famous method for solving this problem, using Bottom-Up algorithm. We tested our method on merged TIMIT files, and recordings we recorded by ourselves.

Poster for Speaker Diarization Using Dimension Reduction