Performance Comparison of Korean Dialect Classification Models Based on Acoustic Features (음향 특성에 따른 한국어 방언 분류 모델의 성능 비교)

Young-Kook Kim (김영국); Myung-Ho Kim (김명호)

doi:10.9708/jksci.2021.26.10.037

Performance Comparison of Korean Dialect Classification Models Based on Acoustic Features

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2021, 26(10), pp.37-43
DOI : 10.9708/jksci.2021.26.10.037
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : September 15, 2021
Accepted : October 25, 2021
Published : October 29, 2021

Young-Kook Kim ¹, Myung-Ho Kim ²

¹숭실대학교 융합소프트웨어학과
²숭실대학교

Accredited

ABSTRACT

Using the acoustic features of speech, important social and linguistic information about the speaker can be obtained, and one of the key features is the dialect. A speaker's use of a dialect is a major barrier to interaction with a computer. Dialects can be distinguished at various levels such as phonemes, syllables, words, phrases, and sentences, but it is difficult to distinguish dialects by identifying them one by one. Therefore, in this paper, we propose a lightweight Korean dialect classification model using only MFCC among the features of speech data. We study the optimal method to utilize MFCC features through Korean conversational voice data, and compare the classification performance of five Korean dialects in Gyeonggi/Seoul, Gangwon, Chungcheong, Jeolla, and Gyeongsang in eight machine learning and deep learning classification models. The performance of most classification models was improved by normalizing the MFCC, and the accuracy was improved by 1.07% and F1-score by 2.04% compared to the best performance of the classification model before normalizing the MFCC.

KEYWORDS

Machine Learning, Deep Learning, MFCC, Dialect Classification, Speech Analysis

Citation status

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

[web] Park Jeon-gyu / Deep Learning-based Speech Recognition Technology / http://www.itdaily.kr/news/articleView.html?idxno=76405

[journal] S. S. Jo / 2017 / AI(Artificial Intelligence)Voice Assistant Evolving to Platform / IITP : 1~25

[confproc] Rongqing Huang / 2005 / Dialect/accent classification via boosted word modeling / IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005. Proceedings (ICASSP’05) / IEEE 1 : I~585

[journal] Thomas Purnell / 1999 / Perceptual and phonetic experiments on american english dialect identification / Journal of language and social psychology 18(1) : 10~30

[journal] Najim Dehak / 2011 / Front-End Factor Analysis for Speaker Verification / IEEE Transactions on Audio, Speech, and Language Processing / Institute of Electrical and Electronics Engineers (IEEE) 19(4) : 788~798

[confproc] Dehak, N. / 2011 / Language recognition via ivectors and dimensionality reduction / Proceedings of the Annual Conference of the International Speech Communication Association : 857~860

[journal] Yan Song / 2013 / i‐vector representation based on bottleneck features for language identification / Electronics Letters / Institution of Engineering and Technology (IET) 49(24) : 1569~1570

[confproc] Snyder, D. / 2018 / Spoken language recognition using x-vectors / Proceedings of Odyssey 2018 The Speaker and Language Recognition Workshop : 105~111

[journal] Charalambos Themistocleous / 2019 / Dialect Classification From a Single Sonorant Sound Using Deep Neural Networks / Frontiers in Communication / Frontiers Media SA 4

[confproc] Nagaratna B. Chittaragi / 2017 / Acoustic features based word level dialect classification using SVM and ensemble methods / IEEE Trans, In 2017 Tenth International Conference on Contemporary Computing (IC3) : 1~6

[confproc] Li, Ming / 2010 / Combining five acoustic level modeling methods for automatic speaker age and gender recognition / Eleventh Annual Conference of the International Speech Communication Association : 2526~2829

[journal] Reynolds, Douglas A. / 2000 / Speaker verification using adapted Gaussian mixture models / Digital signal processing 10 : 19~41

[confproc] Li, Ming / 2007 / Spoken language identification using score vector modeling and support vector machine / Eighth Annual Conference of the International Speech Communication Association : 350~353

[journal] Stolcke, Andreas / 2007 / Speaker recognition with session variability normalization based on MLLR adaptation transforms / IEEE Transactions on Audio, Speech, and Language Processing 15(7) : 1987~1998

[journal] Qawaqneh, Zakariya / 2017 / Deep neural network framework and transformed MFCCs for speaker's age and gender classification / Knowledge-Based Systems 115 : 5~14

[journal] Mallouh, Arafat Abu / 2018 / New transformed features generated by deep bottleneck extractor and a GMM–UBM classifier for speaker age and gender classification / Neural Computing and Applications 30(8) : 2581~2593

[confproc] Ghahremani, P. / 2018 / End-to-end Deep Neural Network Age Estimation / INTERSPEECH : 277~281

[confproc] Snyder, D. / 2018 / X-vectors: Robust dnn embeddings for speaker recognition / 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) : 5329~5333

[journal] Hourri, Soufiane / 2020 / A deep learning approach for speaker recognition / International Journal of Speech Technology 23(1) : 123~131

[other] S. Gopal Krishna Patro / 2015 / Normalization:A Preprocessing Stage / arXiv preprint arXiv:1503.06462

[confproc] Goutte, Cyril / 2005 / A probabilistic interpretation of precision, recall and F-score, with implication for evaluation / European conference on information retrieval / Springer : 345~359

[web] AI Hub / Korean Conversation Voice / https://aihub.or.kr/aidata/7968

KJCKorea
Journal Central

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

Performance Comparison of Korean Dialect Classification Models Based on Acoustic Features

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

Performance Comparison of Korean Dialect Classification Models Based on Acoustic Features

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (1)

REFERENCES (22) * References for papers published after 2023 are currently being built.

Search PDF

Citation

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