dc.contributor.advisor | Ghosh, Prasanta Kumar | |
dc.contributor.author | Karjol, Pavan Subhaschandra | |
dc.date.accessioned | 2021-07-08T10:13:47Z | |
dc.date.available | 2021-07-08T10:13:47Z | |
dc.date.submitted | 2018 | |
dc.identifier.uri | https://etd.iisc.ac.in/handle/2005/5190 | |
dc.description.abstract | Speech enhancement is at the heart of many applications such as speech com-
munication, automatic speech recognition, hearing aids etc. In this work, we
consider the speech enhancement under the framework of multiple deep neural
network (DNN) system. DNNs have been extensively used in speech enhance-
ment due to its ability to capture complex variations in the input data. As
a natural extension, researchers have used variants of a network with multi-
ple DNNs for speech enhancement. Input data could be clustered to train each
DNN or train all the DNNs jointly without any clustering. In this work, we pro-
pose clustering methods for training multiple DNN systems and its variants for
speech enhancement. One of the proposed works involves grouping phonemes
into broad classes and training separate DNN for each class. Such an approach is
found to perform better than single DNN based speech enhancement. However,
it relies on phoneme information which may not be available for all corpora.
Hence, we propose a hard expectation-maximization (EM) based task speci c
clustering method, which, automatically determines clusters without relying on
the knowledge of speech units. The idea is to redistribute the data points among
multiple DNNs such that it enables better speech enhancement. The experimen-
tal results show that the hard EM based clustering performs better than the
single DNN based speech enhancement and provides results similar to that of
the broad phoneme class based approach. | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | ;G29477 | |
dc.rights | I grant Indian Institute of Science the right to archive and to make available my thesis or dissertation in whole or in part in all forms of media, now hereafter known. I retain all proprietary rights, such as patent rights. I also retain the right to use in future works (such as articles or books) all or part
of this thesis or dissertation | en_US |
dc.subject | deep neural network | en_US |
dc.subject | Speech enhancement | en_US |
dc.subject.classification | Research Subject Categories::TECHNOLOGY::Electrical engineering, electronics and photonics::Electrical engineering | en_US |
dc.title | Speech enhancement using deep mixture of experts | en_US |
dc.type | Thesis | en_US |
dc.degree.name | MS | en_US |
dc.degree.level | Masters | en_US |
dc.degree.grantor | Indian Institute of Science | en_US |
dc.degree.discipline | Engineering | en_US |