Speech enhancement using deep mixture of experts based on hard expectation maximization

Karjol, Pavan and Ghosh, Prasanta Kumar (2018) Speech enhancement using deep mixture of experts based on hard expectation maximization. In: 19th Annual Conference of the International Speech Communication, INTERSPEECH 2018, 2-6, September 2018, Hyderabad International Convention Centre (HICC)Hyderabad; India, pp. 3254-3258.

PDF int_sep_3254-3258_2018.pdf - Published Version Restricted to Registered users only Download (298kB) | Request a copy

Abstract

We consider the problem of deep mixture of experts based speech enhancement. The deep mixture of experts, where experts are considered as deep neural network (DNN), is difficult to train due to the network structure. In this work, we propose a pre -training method for individual DNN in deep mixture of experts. We use hard expectation maximization (EM) to pre -train the individual DNNs. After pre -training, we take a weighted combination of outputs of individual DNN experts and jointly train the whole system. We compare the proposed method with single DNN based speech enhancement scheme. Speech enhancement experiments, in four SNR conditions, show the superiority of the proposed method over the baseline scheme. The average improvements obtained for four seen noise cases over single DNN scheme are 0.08, 0.59 dB and 0.015 in terms of objective measures viz perceptual evaluation of speech quality (PESQ), segmental signal to noise ratio (seg SNR) and short time objective intelligibility (STOI) respectively.

Item Type:	Conference Paper
Series.:	Interspeech
Publisher:	ISCA-INT SPEECH COMMUNICATION ASSOC
Additional Information:	19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018), Hyderabad, INDIA, AUG 02-SEP 06, 2018
Keywords:	Deep neural networks; Hard expectation maximization; Speech enhancement
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	13 Aug 2020 08:55
Last Modified:	13 Aug 2020 08:55
URI:	http://eprints.iisc.ac.in/id/eprint/62934

Actions (login required)

View Item