Construction and Analysis of Impression Caption Dataset for Environmental Sounds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913557087518720 |
|---|---|
| author | Okamoto, Yuki Nagase, Ryotaro Okamoto, Minami Saito, Yuki Imoto, Keisuke Fukumori, Takahiro Yamashita, Yoichi |
| author_facet | Okamoto, Yuki Nagase, Ryotaro Okamoto, Minami Saito, Yuki Imoto, Keisuke Fukumori, Takahiro Yamashita, Yoichi |
| contents | Some datasets with the described content and order of occurrence of sounds have been released for conversion between environmental sound and text. However, there are very few texts that include information on the impressions humans feel, such as "sharp" and "gorgeous," when they hear environmental sounds. In this study, we constructed a dataset with impression captions for environmental sounds that describe the impressions humans have when hearing these sounds. We used ChatGPT to generate impression captions and selected the most appropriate captions for sound by humans. Our dataset consists of 3,600 impression captions for environmental sounds. To evaluate the appropriateness of impression captions for environmental sounds, we conducted subjective and objective evaluations. From our evaluation results, we indicate that appropriate impression captions for environmental sounds can be generated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15532 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Construction and Analysis of Impression Caption Dataset for Environmental Sounds Okamoto, Yuki Nagase, Ryotaro Okamoto, Minami Saito, Yuki Imoto, Keisuke Fukumori, Takahiro Yamashita, Yoichi Sound Audio and Speech Processing Some datasets with the described content and order of occurrence of sounds have been released for conversion between environmental sound and text. However, there are very few texts that include information on the impressions humans feel, such as "sharp" and "gorgeous," when they hear environmental sounds. In this study, we constructed a dataset with impression captions for environmental sounds that describe the impressions humans have when hearing these sounds. We used ChatGPT to generate impression captions and selected the most appropriate captions for sound by humans. Our dataset consists of 3,600 impression captions for environmental sounds. To evaluate the appropriateness of impression captions for environmental sounds, we conducted subjective and objective evaluations. From our evaluation results, we indicate that appropriate impression captions for environmental sounds can be generated. |
| title | Construction and Analysis of Impression Caption Dataset for Environmental Sounds |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.15532 |