Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima

Yasemin Turkan; F. Boray Tek

doi:10.1109/SIU49456.2020.9302186

Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima

Translated title of the contribution: Using Adaptive Locally Connected Layer in Attention Based Deep Neural Network for Speech Command Recognition

Yasemin Turkan, F. Boray Tek

Isik University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Speech command recognition is an active research topic associated with the human-machine interface. Such problems can be successfully solved with attention-based deep networks. In this study, we improved one of the existing attentionbased deep network methods by using an adaptive locally connected (focused) layer. In the experiments we used Google and Kaggle datasets, which were also used in the reference. We observed that the recognition results can be improved significantly (2.6%) by the attention based deep network which uses adaptive locally connected layers.

Translated title of the contribution	Using Adaptive Locally Connected Layer in Attention Based Deep Neural Network for Speech Command Recognition
Original language	Turkish
Title of host publication	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728172064
DOIs	https://doi.org/10.1109/SIU49456.2020.9302186
Publication status	Published - 5 Oct 2020
Externally published	Yes
Event	28th Signal Processing and Communications Applications Conference, SIU 2020 - Gaziantep, Turkey Duration: 5 Oct 2020 → 7 Oct 2020

Publication series

Name	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

Conference

Conference	28th Signal Processing and Communications Applications Conference, SIU 2020
Country/Territory	Turkey
City	Gaziantep
Period	5/10/20 → 7/10/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Access to Document

10.1109/SIU49456.2020.9302186

Cite this

Turkan, Y., & Tek, F. B. (2020). Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings Article 9302186 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU49456.2020.9302186

Turkan, Yasemin ; Tek, F. Boray. / Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima. 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

@inproceedings{f925361bb9a145429933d9e87faf0bdb,

title = "Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima",

abstract = "Speech command recognition is an active research topic associated with the human-machine interface. Such problems can be successfully solved with attention-based deep networks. In this study, we improved one of the existing attentionbased deep network methods by using an adaptive locally connected (focused) layer. In the experiments we used Google and Kaggle datasets, which were also used in the reference. We observed that the recognition results can be improved significantly (2.6%) by the attention based deep network which uses adaptive locally connected layers.",

keywords = "adaptive locally connected neuron, artificial neural networks, attention, speech command recognition",

author = "Yasemin Turkan and Tek, {F. Boray}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 28th Signal Processing and Communications Applications Conference, SIU 2020 ; Conference date: 05-10-2020 Through 07-10-2020",

year = "2020",

month = oct,

day = "5",

doi = "10.1109/SIU49456.2020.9302186",

language = "T{\"u}rk{\c c}e",

series = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

address = "United States",

}

Turkan, Y & Tek, FB 2020, Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima. in 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings., 9302186, 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Turkey, 5/10/20. https://doi.org/10.1109/SIU49456.2020.9302186

Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima. / Turkan, Yasemin; Tek, F. Boray.
2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9302186 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima

AU - Turkan, Yasemin

AU - Tek, F. Boray

PY - 2020/10/5

Y1 - 2020/10/5

N2 - Speech command recognition is an active research topic associated with the human-machine interface. Such problems can be successfully solved with attention-based deep networks. In this study, we improved one of the existing attentionbased deep network methods by using an adaptive locally connected (focused) layer. In the experiments we used Google and Kaggle datasets, which were also used in the reference. We observed that the recognition results can be improved significantly (2.6%) by the attention based deep network which uses adaptive locally connected layers.

AB - Speech command recognition is an active research topic associated with the human-machine interface. Such problems can be successfully solved with attention-based deep networks. In this study, we improved one of the existing attentionbased deep network methods by using an adaptive locally connected (focused) layer. In the experiments we used Google and Kaggle datasets, which were also used in the reference. We observed that the recognition results can be improved significantly (2.6%) by the attention based deep network which uses adaptive locally connected layers.

KW - adaptive locally connected neuron

KW - artificial neural networks

KW - attention

KW - speech command recognition

UR - http://www.scopus.com/inward/record.url?scp=85100315398&partnerID=8YFLogxK

U2 - 10.1109/SIU49456.2020.9302186

DO - 10.1109/SIU49456.2020.9302186

M3 - Konferans katkısı

AN - SCOPUS:85100315398

T3 - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

BT - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 28th Signal Processing and Communications Applications Conference, SIU 2020

Y2 - 5 October 2020 through 7 October 2020

ER -

Turkan Y, Tek FB. Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9302186. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). doi: 10.1109/SIU49456.2020.9302186

Uyarlanir Yerel Bagli Katman Kullanan Dikkat Tabanli Derin Ag ile Sesli Komut Tanima

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this