Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation
This paper proposes an audio data augmentation method based on deep learning in order to improve the performance of dereverberation. Conventionally, audio data are augmented using a room impulse response, which is artificially generated by some methods, such as the image method. The proposed method...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/2/592 |
| _version_ | 1797490499198648320 |
|---|---|
| author | Deokgyu Yun Seung Ho Choi |
| author_facet | Deokgyu Yun Seung Ho Choi |
| author_sort | Deokgyu Yun |
| collection | DOAJ |
| description | This paper proposes an audio data augmentation method based on deep learning in order to improve the performance of dereverberation. Conventionally, audio data are augmented using a room impulse response, which is artificially generated by some methods, such as the image method. The proposed method estimates a reverberation environment model based on a deep neural network that is trained by using clean and recorded audio data as inputs and outputs, respectively. Then, a large amount of a real augmented database is constructed by using the trained reverberation model, and the dereverberation model is trained with the augmented database. The performance of the augmentation model was verified by a log spectral distance and mean square error between the real augmented data and the recorded data. In addition, according to dereverberation experiments, the proposed method showed improved performance compared with the conventional method. |
| first_indexed | 2024-03-10T00:33:50Z |
| format | Article |
| id | doaj.art-d6e19364f3a848b7aac0c31b17414fde |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:33:50Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d6e19364f3a848b7aac0c31b17414fde2023-11-23T15:21:14ZengMDPI AGSensors1424-82202022-01-0122259210.3390/s22020592Deep Learning-Based Estimation of Reverberant Environment for Audio Data AugmentationDeokgyu Yun0Seung Ho Choi1Department of Electronic Engineering, Seoul National University of Science and Technology, Seoul 139-743, KoreaDepartment of Electronic and IT Media Engineering, Seoul National University of Science and Technology, Seoul 139-743, KoreaThis paper proposes an audio data augmentation method based on deep learning in order to improve the performance of dereverberation. Conventionally, audio data are augmented using a room impulse response, which is artificially generated by some methods, such as the image method. The proposed method estimates a reverberation environment model based on a deep neural network that is trained by using clean and recorded audio data as inputs and outputs, respectively. Then, a large amount of a real augmented database is constructed by using the trained reverberation model, and the dereverberation model is trained with the augmented database. The performance of the augmentation model was verified by a log spectral distance and mean square error between the real augmented data and the recorded data. In addition, according to dereverberation experiments, the proposed method showed improved performance compared with the conventional method.https://www.mdpi.com/1424-8220/22/2/592audio data augmentationdereverberationdeep learningroom impulse response |
| spellingShingle | Deokgyu Yun Seung Ho Choi Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation Sensors audio data augmentation dereverberation deep learning room impulse response |
| title | Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation |
| title_full | Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation |
| title_fullStr | Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation |
| title_full_unstemmed | Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation |
| title_short | Deep Learning-Based Estimation of Reverberant Environment for Audio Data Augmentation |
| title_sort | deep learning based estimation of reverberant environment for audio data augmentation |
| topic | audio data augmentation dereverberation deep learning room impulse response |
| url | https://www.mdpi.com/1424-8220/22/2/592 |
| work_keys_str_mv | AT deokgyuyun deeplearningbasedestimationofreverberantenvironmentforaudiodataaugmentation AT seunghochoi deeplearningbasedestimationofreverberantenvironmentforaudiodataaugmentation |