Using Deep Neural Networks for Identification of Slavic Languages from Acoustic Signal

Simple item page
dc.contributor.authorMatějů, Lukáš
dc.contributor.authorČerva, Petr
dc.contributor.authorŽďánský, Jindřich
dc.contributor.authorŠafařík, Radek
dc.date.accessioned2019-07-31T09:33:41Z
dc.date.available2019-07-31T09:33:41Z
dc.date.issued2018
dc.description.abstractThis paper investigates the use of deep neural networks (DNNs) for the task of spoken language identification. Various feed-forward fully connected, convolutional and recurrent DNN architectures are adopted and compared against a baseline i-vector based system. Moreover, DNNs are also utilized for extraction of bottleneck features from the input signal. The dataset used for experimental evaluation contains utterances belonging to languages that are all related to each other and sometimes hard to distinguish even for human listeners: it is compiled from recordings of the 11 most widespread Slavic languages. We also released this Slavic dataset to the general public, because a similar collection is not publicly available through any other source. The best results were yielded by a bidirectional recurrent DNN with gated recurrent units that was fed by bottleneck features. In this case, the baseline ER was reduced from 4.2% to 1.2% and C-avg from 2.3% to 0.6%.cs
dc.format.extent5 strancs
dc.identifier.doi10.21437/Interspeech.2018-1165
dc.identifier.urihttps://dspace.tul.cz/handle/15240/153022
dc.identifier.urihttps://www.isca-speech.org/archive/Interspeech_2018/pdfs/1165.pdf
dc.language.isocscs
dc.relation.ispartof19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES
dc.subjectrecurrent neural networkscs
dc.subjectconvolutional neural networkscs
dc.subjectdeep neural networkscs
dc.subjectSlavic languagescs
dc.subjectlanguage identificationcs
dc.titleUsing Deep Neural Networks for Identification of Slavic Languages from Acoustic Signalcs
local.citation.epage1807
local.citation.spage1803
local.event.edate2018-09-06
local.event.locationHyderabad, INDIA
local.event.sdate2018-08-02
local.event.title19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018)
local.identifier.publikace6130
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Using Deep Neural Networks for Identification of Slavic Languages from Acoustic Signal.pdf
Size:
214.47 KB
Format:
Adobe Portable Document Format
Description:
článek
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections