Electrical Engineering-Systems Dept.

סמינר מחלקתי

You are invited to attend a lecture by

Dr. Hagai Aronowitz

(IBM Haifa Research Lab)

on the subject:

Intra-class Variability Modeling for Speech Processing

Most  speech  recognition related tasks may be formulated as classification tasks. Until recently, the state-of-the-art approach for speech classification was  based on an assumption that an observed segment is actually a sequence of short frames drawn independently from a class-dependent distribution which is modeled by a Gaussian mixture model.

Our approach is to represent every speech segment as a distribution over the frame-space, and to model every class as a prior distribution over the segment-distribution-space.

We describe how this approach leads to improved speaker recognition and speaker diarization algorithms.