Yoon-Joong Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yoon-Joong Kim has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Arnel C. Fajardo
Hanbat National University / La Consolacion College Manila
1 shared publication - Yeonguk Yu
Gwangju Institute of Science and Technology (GIST)
1 shared publication - You-Jung Ko1 shared publication
Latest Publications
- Open Access
- 26 April 2020
- Published by MDPI AG in Electronics
- Vol. 9 (5) , 713
Attention-LSTM-Attention Model for Speech Emotion Recognition and Analysis of IEMOCAP Database
We propose a speech-emotion recognition (SER) model with an “attention-long Long Short-Term Memory (LSTM)-attention” component to combine IS09, a commonly used feature for SER, and mel spectrogram, and we analyze the reliability problem of the interactive emotional dyadic motion capture (IEMOCAP) database. The attention mechanism of the model focuses on emotion-related elements of the IS09 and mel spectrogram feature and the emotion-related duration from the time of the feature. Thus, the model extracts emotion information from a given speech signal. The proposed model for the baseline study achieved a weighted accuracy (WA) of 68% for the improvised dataset of IEMOCAP. However, the WA of the proposed model of the main study and modified models could not achieve more than 68% in the improvised dataset. This is because of the reliability limit of the IEMOCAP dataset. A more reliable dataset is required for a more accurate evaluation of the model’s performance. Therefore, in this study, we reconstructed a more reliable dataset based on the labeling results provided by IEMOCAP. The experimental results of the model for the more reliable dataset confirmed a WA of 73%.
- 26 April 2020
- Published by MDPI AG in Electronics
- Vol. 9 (5) , 713
Open AccessAttention-LSTM-Attention Model for Speech Emotion Recognition and Analysis of IEMOCAP Database
We propose a speech-emotion recognition (SER) model with an “attention-long Long Short-Term Memory (LSTM)-attention” component to combine IS09, a commonly used feature for SER, and mel spectrogram, and we analyze the reliability problem of the interactive emotional dyadic motion capture (IEMOCAP) database. The attention mechanism of the model focuses on emotion-related elements of the IS09 and mel spectrogram feature and the emotion-related duration from the time of the feature. Thus, the model extracts emotion information from a given speech signal. The proposed model for the baseline study achieved a weighted accuracy (WA) of 68% for the improvised dataset of IEMOCAP. However, the WA of the proposed model of the main study and modified models could not achieve more than 68% in the improvised dataset. This is because of the reliability limit of the IEMOCAP dataset. A more reliable dataset is required for a more accurate evaluation of the model’s performance. Therefore, in this study, we reconstructed a more reliable dataset based on the labeling results provided by IEMOCAP. The experimental results of the model for the more reliable dataset confirmed a WA of 73%.
- 30 November 2019
- Published by Korean Institute of Information Technology in The Journal of Korean Institute of Information Technology
- Vol. 17 (11) , 77-85
Performance Improvement of Speech Emotion Recognition Model Using Generative Adversarial Networks
최근 딥 러닝 모델의 발전에 따라 음성 감정 인식 모델의 성능 개선이 이루어지고 있으나 충분한 학습 데이터 확보의 어려움은 여전히 성능 개선의 저하 요인이다. 본 논문은 Generative Adversarial Network(GAN)으로 부정 감정 데이터를 생성하여 부정 데이터 학습을 추가함으로써 음성 감정 인식 모델의 성능을 개선하는 방법을 제안한다. 제안된 시스템은 감정 인식 판별기, 감정 신호 생성기로 구성되어 있다. 생성기는 부정 감정신호와 부정 레이블을 만들어 학습 데이터 셋을 보완하고, 판별기는 실제 감정 신호와 부정 감정 신호가 포함된 학습 데이터 셋으로 훈련된다. 실험은 IEMOCAP 데이터 셋을 사용하였고 다양한 인식 모델을 구성하여 인식률을 비교한 결과 GAN을 추가한 감정 인식기가 BLSTM과 Attention을 이용한 감정 인식 모델에 비해 1.86% 더 정확한 예측을 제공하는 것으로 나타났다.
- 30 November 2019
- Published by Korean Institute of Information Technology in The Journal of Korean Institute of Information Technology
- Vol. 17 (11) , 77-85
Performance Improvement of Speech Emotion Recognition Model Using Generative Adversarial Networks
최근 딥 러닝 모델의 발전에 따라 음성 감정 인식 모델의 성능 개선이 이루어지고 있으나 충분한 학습 데이터 확보의 어려움은 여전히 성능 개선의 저하 요인이다. 본 논문은 Generative Adversarial Network(GAN)으로 부정 감정 데이터를 생성하여 부정 데이터 학습을 추가함으로써 음성 감정 인식 모델의 성능을 개선하는 방법을 제안한다. 제안된 시스템은 감정 인식 판별기, 감정 신호 생성기로 구성되어 있다. 생성기는 부정 감정신호와 부정 레이블을 만들어 학습 데이터 셋을 보완하고, 판별기는 실제 감정 신호와 부정 감정 신호가 포함된 학습 데이터 셋으로 훈련된다. 실험은 IEMOCAP 데이터 셋을 사용하였고 다양한 인식 모델을 구성하여 인식률을 비교한 결과 GAN을 추가한 감정 인식기가 BLSTM과 Attention을 이용한 감정 인식 모델에 비해 1.86% 더 정확한 예측을 제공하는 것으로 나타났다.
- Open Access
- 15 August 2014
- Published by Walter de Gruyter GmbH in Balkan Region Conference on Engineering and Business Education
- Vol. 1 (1) , 531-536
Test Of Vowels In Speech Recognition Using Continuous Density Hidden Markov Model And Development Of Phonetically Balanced-Words In The Filipino Language
- 15 August 2014
- Published by Walter de Gruyter GmbH in Balkan Region Conference on Engineering and Business Education
- Vol. 1 (1) , 531-536
Open AccessTest Of Vowels In Speech Recognition Using Continuous Density Hidden Markov Model And Development Of Phonetically Balanced-Words In The Filipino Language