BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917693928505344 |
|---|---|
| author | Kim, June-Woo Toikkanen, Miika Choi, Yera Moon, Seoung-Eun Jung, Ho-Young |
| author_facet | Kim, June-Woo Toikkanen, Miika Choi, Yera Moon, Seoung-Eun Jung, Ho-Young |
| contents | Respiratory sound classification (RSC) is challenging due to varied acoustic signatures, primarily influenced by patient demographics and recording environments. To address this issue, we introduce a text-audio multimodal model that utilizes metadata of respiratory sounds, which provides useful complementary information for RSC. Specifically, we fine-tune a pretrained text-audio multimodal model using free-text descriptions derived from the sound samples' metadata which includes the gender and age of patients, type of recording devices, and recording location on the patient's body. Our method achieves state-of-the-art performance on the ICBHI dataset, surpassing the previous best result by a notable margin of 1.17%. This result validates the effectiveness of leveraging metadata and respiratory sound samples in enhancing RSC performance. Additionally, we investigate the model performance in the case where metadata is partially unavailable, which may occur in real-world clinical setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06786 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification Kim, June-Woo Toikkanen, Miika Choi, Yera Moon, Seoung-Eun Jung, Ho-Young Sound Artificial Intelligence Audio and Speech Processing Respiratory sound classification (RSC) is challenging due to varied acoustic signatures, primarily influenced by patient demographics and recording environments. To address this issue, we introduce a text-audio multimodal model that utilizes metadata of respiratory sounds, which provides useful complementary information for RSC. Specifically, we fine-tune a pretrained text-audio multimodal model using free-text descriptions derived from the sound samples' metadata which includes the gender and age of patients, type of recording devices, and recording location on the patient's body. Our method achieves state-of-the-art performance on the ICBHI dataset, surpassing the previous best result by a notable margin of 1.17%. This result validates the effectiveness of leveraging metadata and respiratory sound samples in enhancing RSC performance. Additionally, we investigate the model performance in the case where metadata is partially unavailable, which may occur in real-world clinical setting. |
| title | BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.06786 |