Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F16%3APU122427" target="_blank" >RIV/00216305:26230/16:PU122427 - isvavai.cz</a>
Result on the web
<a href="https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition" target="_blank" >https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2016-1584" target="_blank" >10.21437/Interspeech.2016-1584</a>
Alternative languages
Result language
angličtina
Original language name
Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition
Original language description
The most popular way to apply Deep Neural Network (DNN) for Language IDentification (LID) involves the extraction of bottleneck features from a network that was trained on automatic speech recognition task. These features are modeled using a classical I-vector system. Recently, a more direct DNN approach was proposed, it consists of estimating the language posteriors directly from a stacked frames input. The final decision score is based on averaging the scores for all the frames for a given speech segment. In this paper, we extended the direct DNN approach by modeling all hidden-layer activations rather than just averaging the output scores. One super-vector per utterance is formed by concatenating all hidden-layer responses. The dimensionality of this vector is then reduced using a Principal Component Analysis (PCA). The obtained reduce vector summarizes the most discriminative features for language recognition based on the trained DNNs. We evaluated this approach in NIST 2015 language recognition evaluation. The performances achieved by the proposed approach are very competitive to the classical I-vector baseline.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
N - Vyzkumna aktivita podporovana z neverejnych zdroju
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of Interspeech 2016
ISBN
978-1-5108-3313-5
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
2365-2369
Publisher name
International Speech Communication Association
Place of publication
San Francisco
Event location
San Francisco
Event date
Sep 8, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000409394402034