한국어 음성을 이용한 연령 분류 딥러닝 알고리즘 기술 개발
Development of Age Classification Deep Learning Algorithm Using Korean Speech
3
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
In modern society, speech recognition technology is emerging as an important technology for identification in electronic commerce, forensics, law enforcement, and other systems. In this study, we aim to develop an age classification algorithm for extracting only MFCC(Mel Frequency Cepstral Coefficient) expressing the characteristics of speech in Korean and applying it to deep learning technology. The algorithm for extracting the 13th order MFCC from Korean data and constructing a data set, and using the artificial intelligence algorithm, deep artificial neural network, to classify males in their 20s, 30s, and 50s, and females in their 20s, 40s, and 50s. finally, our model confirmed the classification accuracy of 78.6% and 71.9% for males and females, respectively.
Abstract
In modern society, speech recognition technology is emerging as an important technology for identification in electronic commerce, forensics, law enforcement, and other systems. In this study, we aim to develop an age classification algorithm for extracting only MFCC(Mel Frequency Cepstral Coefficient) expressing the characteristics of speech in Korean and applying it to deep learning technology. The algorithm for extracting the 13th order MFCC from Korean data and constructing a data set, and using the artificial intelligence algorithm, deep artificial neural network, to classify males in their 20s, 30s, and 50s, and females in their 20s, 40s, and 50s. finally, our model confirmed the classification accuracy of 78.6% and 71.9% for males and females, respectively.
참고문헌 (14)
- J.H.L. Hansen, "Speaker recognition by machines and humans: A tutorial review", IEEE Signal Proc. Mag., 32(6), pp.74~99 (2015)[DOI]
- Schuller, B., "The INTERSPEECH 2010 Paralinguistic Challenge", Proc. INTERSPEECH 2010, Makuhari, Japan, pp.2794~2797 (2010)
- M. Li, "Automatic speaker age and gender recognition using acoustic and prosodic level information fusion", Computer Speech & Language, 27(1), pp.151~167 (2013)[DOI]
- Phuoc Nguyen, "Fuzzy support vector machines for age and gender classification", NTERSPEECH 2010, pp.2806~2809 (2010)
- 강우현, "I-벡터 특징을 이용하는 NN 기반의 화자 연령 분류", 한국통신학회 학술대회논문집, pp.589~590 (2015)
- Logan, Beth, "Mel Frequency Cepstral Coefficients for Music Modeling", ISMIR, 270 (2000)
- Y. LeCun, "Deep learning", Nature, 521 (2015)
- Katerenchuk, Denys, "Age Group Classification with Speech and Metadata Multimodality Fusion", Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2 (2017)
- 윤태진, "한국어 대용량발화말뭉치의 단모음분석", 말소리와 음성과학, 6(3), pp.139~145 (2014), 한국음성학회[DOI]
- Muda, L., "Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques", arXiv preprint arXiv:1003.4083, ~ (2010)
- D. Mahmoodi, "Age estimation based on speech features and support vector machine", Proceedings of the 3rd Computer Science and Electronic Engineering Conference (CEEC '11), pp.60~64 (2011)
- "Speech Emotion Recognition by AdaBoost Algorithm and Feature Selection for Support Vector Machines"[URL]
- KINGMA, Diederik P, "Adam: A method for stochastic optimization", arXiv preprint arXiv:1412.6980, ~ (2014)
- B. D. Barkana, "A new pitch-range based feature set for a speaker's age and gender classification", Appl. Acoust., 98, pp.52~61 (2015)[DOI]