Combining Two Different DNN Architectures for Classifying Speaker’s Age and Gender

Arafat Abu Mallouh, Zakariya Qawaqneh, Buket D. Barkana

2017

Abstract

Speakers’ age and gender classification is one of the most challenging problems in the field of speech processing. Recently, remarkable developments have been achieved in the neural network field, nowadays, deep neural network (DNN) is considered one of the state-of-art classifiers which have been successful in many speech applications. Motivated by DNN success, we jointly fine-tune two different DNNs to classify the speaker’s age and gender. The first DNN is trained to classify the speaker gender, while the second DNN is trained to classify the age of the speaker. Then, the two pre-trained DNNs are reused to tune a third DNN (AGender-Tuning) which can classify the age and gender of the speaker together. The results show an improvement in term of accuracy for the proposed work compared with the I-Vector and the GMM-UBM as baseline systems. Also, the performance of the proposed work is compared with other published works on a publicly available database.

Paper Citation

in Harvard Style

Abu Mallouh A., Qawaqneh Z. and Barkana B. (2017). Combining Two Different DNN Architectures for Classifying Speaker’s Age and Gender. In - BIOSIGNALS, (BIOSTEC 2017) ISBN , pages 0-0. DOI: 10.5220/0006096500001488

in Bibtex Style

@conference{biosignals17,
author={Arafat Abu Mallouh and Zakariya Qawaqneh and Buket D. Barkana},
title={Combining Two Different DNN Architectures for Classifying Speaker’s Age and Gender},
booktitle={ - BIOSIGNALS, (BIOSTEC 2017)},
year={2017},
pages={},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006096500001488},
isbn={},
}

in EndNote Style

TY - CONF

JO - - BIOSIGNALS, (BIOSTEC 2017)
TI - Combining Two Different DNN Architectures for Classifying Speaker’s Age and Gender
SN -
AU - Abu Mallouh A.
AU - Qawaqneh Z.
AU - Barkana B.
PY - 2017
SP - 0
EP - 0
DO - 10.5220/0006096500001488