← Search

Maryam Najafian

2 accepted papers

2018

Exploiting Convolutional Neural Networks for Phonotactic Based Dialect Identification

ICASSP 2018accepted

In this paper, we investigate different approaches for Dialect Identification (DID) in Arabic broadcast speech. Dialects differ in their inventory of phonological segments. This paper proposes a new phonotactic based feature representation approach which enables discrimination among different occurr…

Cited by 0SourceScholar
2017

Environment aware speaker diarization for moving targets using parallel DNN-based recognizers

ICASSP 2017accepted

Current diarization algorithms are commonly applied to the outputs of single non-moving microphones. They do not explicitly identify the content of overlapped segments from multiple speakers or acoustic events. This paper presents an acoustic environment aware child-adult diarization applied to the…

Cited by 0SourceScholar