An Automatic Data Construction Approach for Korean Speech Command Recognition (한국어 음성 명령어 인식을 위한 자동데이터 구축)

Yeonsoo Lim (임연수); Deokjin Seo (서덕진); Park， Jeong-Sik (박정식); JUNG YU CHUL (정유철)

doi:10.9708/jksci.2019.24.12.017

An Automatic Data Construction Approach for Korean Speech Command Recognition

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2019, 24(12), pp.17-24
DOI : 10.9708/jksci.2019.24.12.017
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : November 26, 2019
Accepted : December 20, 2019
Published : December 31, 2019

Yeonsoo Lim ¹, Deokjin Seo ¹, Park， Jeong-Sik ², JUNG YU CHUL ¹

¹금오공과대학교
²한국외국어대학교

Accredited

ABSTRACT

The biggest problem in the AI field, which has become a hot topic in recent years, is how to deal with the lack of training data. Since manual data construction takes a lot of time and efforts, it is non-trivial for an individual to easily build the necessary data. On the other hand, automatic data construction needs to handle data quality issue. In this paper, we introduce a method to automatically extract the data required to develop Korean speech command recognizer from the web and to automatically select the data that can be used for training data. In particular, we propose a modified ResNet model that shows modest performance for the automatically constructed Korean speech command data. We conducted an experiment to show the applicability of the command set of the health and daily life domain. In a series of experiments using only automatically constructed data, the accuracy of the health domain was 89.5% in ResNet15 and 82% in ResNet8 in the daily lives domain, respectively.

KEYWORDS

Korean Speech Command, Speech Recognition, Automatic Data Construction, ResNet, CNN

Citation status

* References for papers published after 2023 are currently being built.

[other] E. Lakomkin / 2019 / KT-Speech-Crawler : Automatic Dataset Construction for Speech Recognition from YouTube Videos / arXiv : 1903. 00216

[web] / Zeroth project / https://github.com/goodatlas/zeroth

[web] / KSS data set / https://www.kaggle.com/bryanpark/korean-single-speaker-speech-dataset

[confproc] J. Kaewprateep / 2018 / Evaluation of small-scale deep learning architectures in Thai speech recognition / 1st Int. ECTI North. Sect. Conf. Electr. Electron. Comput. Telecommun. Eng. ECTI-NCON 2018 : 60~64

[confproc] Y. Choi / 2018 / Pansori : ASR Corpus Generation from Open Online Video Contents / IEEE Seoul Sect. Student Pap. Contest : 117~121

[confproc] H. Zhang / 2018 / MixUp : Beyond empirical risk minimization / 6th Int. Conf. Learn. Represent. ICLR 2018 - Conf. Track Proc : 1~13

[confproc] T. N. Sainath / 2015 / Convolutional Neural Networks for Small-footprint Keyword Spotting / Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH : 1478~1482

[other] R. Tang / 2017 / Honk : A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting / arXiv : 1710. 06554

[confproc] G. Chen / 2014 / Small-footprint keyword spotting using deep neural networks / ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc : 4087~4091

[other] P. Warden / 2018 / Speech Commands : A Dataset for Limited-Vocabulary Speech Recognition / arXiv : 1804. 03209

[confproc] R. Tang / 2018 / Deep residual learning for small-footprint keyword spotting / ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc. : 5484~5488

[confproc] K. He / 2016 / Deep residual learning for image recognition / Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit : 770~778

[confproc] K. He / 2016 / Identity mappings in deep residual networks / Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9908LNCS : 630~645

[confproc] S. Choi / 2019 / Temporal convolution for real-time keyword spotting on mobile devices / Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH : 3372~3376

[confproc] D. Oneață / 2019 / Kite : Automatic Speech Recognition for Unmanned Aerial Vehicles / Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH : 2998~3002

[other] T. Rajapakshe / 2019 / Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition / arXiv : 1910. 11256

[other] J. Vadillo / 2019 / Universal adversarial examples in speech command classification / arXiv : 1911. 10182

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

An Automatic Data Construction Approach for Korean Speech Command Recognition

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

An Automatic Data Construction Approach for Korean Speech Command Recognition

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (17) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.