Over the course of 2016, assistant professor Najim Dehak served as keynote and invited speaker at two major speech and language conferences. Dr. Dehak also served as the general co-chair to a major language and technology workshop.
- Serving as a keynote speaker at the Odyssey 2016 Speaker and Language Workshop, Dr. Dehak gave his keynote titled I-Vector Representation Based on GMM and DNN for Audio Classification.
The I-vector approach became the state of the art approach in several audio classification tasks such as speaker and language recognition. This approach consists of modeling and capturing all the different variability in the Gaussian Mixture Model (GMM) mean components between several audio recordings. More recently several subspace approaches had been extended on modeling the variability between the GMM weights rather than the GMM means. These last techniques such as Non-negative Factor Analysis (NFA) and Subspace Multinomial Model (SMM) needed to deal with the fact that the GMM weights are always positive and they should sum to one. In this talk, we will show how the NFA and SMM approaches or similar other subspaces approaches can be also used to model the hidden layer neuron activations on the deep neural network model for sequential data recognition task such as language and dialect recognition. - As the general co-chair of the 2016 IEEE Spoken Language Technology (SLT) Workshop, Dr. Dehak worked to ensure that the goal of the conference – an aim to promote the impact of speech and language technologies in human daily life – was fully achieved.
- Professor Najim Dehak was an invited speaker at the joint symposium of SLP(IPSJ), SP(IEICE), and IEEE Signal Processing Society Japan Chapter, held in Tokyo Japan.