no code implementations • 20 Sep 2023 • Bagus Tris Atmaja, Akira Sasou
A Spearman rank correlation coefficient of 0. 537 is reported for the test set, while for the development set, the score is 0. 524.
1 code implementation • ICASSP 2023 • Bagus Tris Atmaja, Akira Sasou
The search for emotional biomarkers within the human voice is a challenging research area.
Ranked #1 on Vocal Bursts Type Prediction on HUME-VB
Automatic Speech Recognition Cultural Vocal Bursts Intensity Prediction +6
1 code implementation • 27 Dec 2022 • Bagus Tris Atmaja, Haris Ihsannur, Suyanto, Dhany Arifianto
The monitoring of machine conditions in a plant is crucial for production in manufacturing.
1 code implementation • APSIPA 2022 • Bagus Tris Atmaja, Akira Sasou
Understanding humans’ emotions is a challenge for computers.
no code implementations • 26 Oct 2022 • Bagus Tris Atmaja, Akira Sasou
Traditional speech emotion recognition (SER) evaluations have been performed merely on a speaker-independent condition; some of them even did not evaluate their result on this condition.
1 code implementation • 12 Oct 2022 • Bagus Tris Atmaja, Zanjabila, Suyanto, Akira Sasou
This paper addresses issues on cough-based COVID-19 detection.
1 code implementation • 5 Oct 2022 • Bagus Tris Atmaja, Zanjabila, Suyanto, Akira Sasou
The results by two automatic segmentation methods obtained precisions of 73% and 70% compared to 49% by manual segmentation.
1 code implementation • 27 Sep 2022 • Bagus Tris Atmaja, Akira Sasou
The studies of predicting affective states from human voices have relied heavily on speech.
Cultural Vocal Bursts Intensity Prediction Speech Recognition
1 code implementation • 21 Jul 2022 • Bagus Tris Atmaja, Zanjabila, Akira Sasou
In this paper, we demonstrated the benefit of using pre-trained model to extract acoustic embedding to jointly predict (multitask learning) three tasks: emotion, age, and native country.
1 code implementation • ICASSP 2020 • Bagus Tris Atmaja, Masato Akagi
A multistage method, employed at the late fusion approach, significantly improved the agreement score between true and pre- dictated values on the development set of data (from [0. 537, 0. 565, 0. 083] to [0. 68, 0. 656, 0. 443]) for arousal, valence, and liking.
1 code implementation • 6 Apr 2020 • Bagus Tris Atmaja, Masato Akagi
Modern deep learning architectures are ordinarily performed on high-performance computing facilities due to the large size of the input features and complexity of its model.
1 code implementation • 1 Apr 2020 • Bagus Tris Atmaja, Masato Akagi
In this paper, we evaluate the different features sets, feature types, and classifiers on both song and speech emotion recognition.
1 code implementation • 24 Mar 2020 • Bagus Tris Atmaja, Masato Akagi
The choice of a loss function is a critical part in machine learning.
1 code implementation • APSIPA ASC 2019 • Bagus Tris Atmaja, Kiyoaki Shirai, and Masato Akagi
Text features can be combined with speech features to improve emotion recognition accuracy, and both features can be obtained from speech.
Ranked #8 on Speech Emotion Recognition on IEMOCAP