PuneettArora's picture
|
download
raw
2.75 kB
---
tags:
- audio-event-detection
pretty_name: 'Barkopedia: Dog Vocal Detection'
size_categories:
- 10K<n<100K
---
# ๐Ÿพ Dog Vocal Detection
This dataset is curated from internet videos to support research in dog vocalization detection using both weak and strong supervision.
- It contains approximately 7,500 seconds of strongly labeled training audio
- Over 9,000 seconds of weakly labeled clips sourced from AudioSet are included.
- The dataset also provides 24 hours of unlabeled audio clips from our own collection.
- To simulate realistic conditions, some clips feature dogs present without barking, reflecting challenging real-world scenarios.
A corresponding validation and test set are available as part of the [Barkopedia Dog Vocal Detection Challenge](https://huggingface.co/spaces/ArlingtonCL2/BarkopediaDogVocalDetectionChallenge) on Hugging Face.
### ๐Ÿ“‚ Folder Structure
```
.
โ”œโ”€โ”€ strong_audios
โ”‚ โ”œโ”€โ”€ UC_Aswv9nASkcjXoXKPVkPiQ+_mMhlYEgxoE+00002_pitbull.wav
โ”‚ โ”œโ”€โ”€ UC_Aswv9nASkcjXoXKPVkPiQ+3sZLaAgADuo+00002_pitbull.wav
โ”‚ โ”œโ”€โ”€ UCeqTOU_4b6UEmPgBdqd4YWg+rwo5lVV3N2I+00000_chihuahua.wav
โ”‚ โ”œโ”€โ”€ ...
โ”‚ โ””โ”€โ”€ UCze-YohIl415Ric6I2SN0ow+SoYhkuSXOZo+00007_shiba_inu.wav
โ”‚
โ”œโ”€โ”€ strong_audios_tsv
โ”‚ โ””โ”€โ”€ train.tsv
โ”‚
โ”œโ”€โ”€ unlabeled_audios
โ”‚ โ”œโ”€โ”€ chihuahua
โ”‚ โ”œโ”€โ”€ UC_WHiJEE5B-QOKpwLyaNcXg+E0VNPqB7c7g+00001.wav
โ”‚ โ”œโ”€โ”€ ...
โ”‚ โ””โ”€โ”€ UC0Qw7Ew6lSPHfAm83sRu_3g+QcHYPW9irkE+00000.wav
โ”‚ โ”œโ”€โ”€ german_shepherd
โ”‚ โ”œโ”€โ”€ husky
โ”‚ โ”œโ”€โ”€ labrador
โ”‚ โ”œโ”€โ”€ pitbull
โ”‚ โ””โ”€โ”€ shiba_inu
โ”‚
โ””โ”€โ”€ weak_audios
โ”œโ”€โ”€ chihuahua
โ”œโ”€โ”€ german_shepherd
โ”œโ”€โ”€ husky
โ”œโ”€โ”€ labrador
โ”œโ”€โ”€ pitbull
โ””โ”€โ”€ shiba_inu
```
where the `train.tsv` takes a format like so:
```
UCkMjjl3JEZpp4sRUJx5eJEA+X-X8s0DXXI8+00004_chihuahua.wav 9.59548 10.01272 dog
UCkMjjl3JEZpp4sRUJx5eJEA+X-X8s0DXXI8+00004_chihuahua.wav 10.30567 11.57513 dog
UCvHJzqB1KZMpZniAVWy3tkA+fSQeU1uAQbc+00001_chihuahua.wav 0.76266 6.85668 dog_noise
UCvHJzqB1KZMpZniAVWy3tkA+fSQeU1uAQbc+00001_chihuahua.wav 7.5288 9.00958 dog
...
```
Specifically, each row should map one wav file from the test set to the onset and offset (in seconds) of a dog or dog_noise event. In particular, a dog event is a continuum of dog bark(s) that lacks any noticable time gaps. A dog noise event is a dog event that occurs simultaneously with noticable noise (eg, human speech or environmental sounds).
### ๐ŸŽ๏ธ Challenge
This training set has been released for use in the [Barkopedia Dog Vocal Detection Challenge](https://huggingface.co/spaces/ArlingtonCL2/BarkopediaDogVocalDetectionChallenge) on Hugging Face.

Xet Storage Details

Size:
2.75 kB
ยท
Xet hash:
1d2ec0d3b88b9d74f7ae7d194a8bcad0b05859c59c7c1f4e3a1a800061370fdf

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.