feat: add the blog post #242
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Is this ready for review? |
ntlhui
requested changes
Dec 19, 2024
| - bioacoustics | ||
| --- | ||
|
|
||
| Our work, "A Deep Learning Approach to the Automated Segmentation of Bird Vocalizations from Weakly Labeled Crowd-sourced Audio" was accepted and presented at NeurIPS 2024 in the "Tackling Climate Change with Machine Learning" Workshop hosted by Climate Change AI! Congrats to the authors: Jacob Ayers, Sean Perry, Samantha Prestrelski, Tianqi Zhang, Ludwig von Schoenfeldt, Mugen Blue, Gabriel Steinberg, Mathias Tobler,Ian Ingram, Curt Schurgers and Ryan Kastner. |
There was a problem hiding this comment.
Check space after Mathias Tobler
| {% include | ||
| img_caption.html | ||
| src="assets/acoustic_species_id/2024_12_18_NeurIPS_Canda_Place.jpg" | ||
| caption="View of Canda Place, an iconic landmark of Vancover. View taken from the east side of the Vancover Convention Center. The confrence actually took place in both buildings with an underground tunnel connecting the two, as seen on the bottom right of the image. Taken by Sean Perry" |
There was a problem hiding this comment.
sp: Canada Place
sp: Vancouver
| caption="View of Canda Place, an iconic landmark of Vancover. View taken from the east side of the Vancover Convention Center. The confrence actually took place in both buildings with an underground tunnel connecting the two, as seen on the bottom right of the image. Taken by Sean Perry" | ||
| %} | ||
|
|
||
| This focused on the issue of weakly labeled datasets, often associated with large bioacoustic crowdsource dataset. Traditional methods frequently use digital signal processing approches to identify the species of interest. This work takes a look at testing these methods with deep learning models. [The paper can be found here](https://www.climatechange.ai/papers/neurips2024/8). Credits to **Mathias Tobler** for frist conceptualizing the idea. |
There was a problem hiding this comment.
sp: large bioacoustic crowdsourced dataset
| caption="View of Canda Place, an iconic landmark of Vancover. View taken from the east side of the Vancover Convention Center. The confrence actually took place in both buildings with an underground tunnel connecting the two, as seen on the bottom right of the image. Taken by Sean Perry" | ||
| %} | ||
|
|
||
| This focused on the issue of weakly labeled datasets, often associated with large bioacoustic crowdsource dataset. Traditional methods frequently use digital signal processing approches to identify the species of interest. This work takes a look at testing these methods with deep learning models. [The paper can be found here](https://www.climatechange.ai/papers/neurips2024/8). Credits to **Mathias Tobler** for frist conceptualizing the idea. |
There was a problem hiding this comment.
sp: digital signal processing approaches
| caption="View of Canda Place, an iconic landmark of Vancover. View taken from the east side of the Vancover Convention Center. The confrence actually took place in both buildings with an underground tunnel connecting the two, as seen on the bottom right of the image. Taken by Sean Perry" | ||
| %} | ||
|
|
||
| This focused on the issue of weakly labeled datasets, often associated with large bioacoustic crowdsource dataset. Traditional methods frequently use digital signal processing approches to identify the species of interest. This work takes a look at testing these methods with deep learning models. [The paper can be found here](https://www.climatechange.ai/papers/neurips2024/8). Credits to **Mathias Tobler** for frist conceptualizing the idea. |
There was a problem hiding this comment.
link maybe only here? and not the whole sentence
|
|
||
| This focused on the issue of weakly labeled datasets, often associated with large bioacoustic crowdsource dataset. Traditional methods frequently use digital signal processing approches to identify the species of interest. This work takes a look at testing these methods with deep learning models. [The paper can be found here](https://www.climatechange.ai/papers/neurips2024/8). Credits to **Mathias Tobler** for frist conceptualizing the idea. | ||
|
|
||
| Key contributions to this work include [PyHa](https://github.com/UCSD-E4E/pyha), the python repository where the main techonologies used in the paper are stored. Credits primarly to **Jacob Ayers** for crediting the repo and vision for the project and **Samantha Prestrelski** for the work has done developing it and carrying out experiments. Further thanks to **Gabriel Steinberg** for his techical contributions with isolation techinques and chunking methods and **Mugen Blue** for his training TweetyNet, which was the most successful method used as seen in the paper. |
There was a problem hiding this comment.
sp: Credits primarily to Jacob Ayer
|
|
||
| This focused on the issue of weakly labeled datasets, often associated with large bioacoustic crowdsource dataset. Traditional methods frequently use digital signal processing approches to identify the species of interest. This work takes a look at testing these methods with deep learning models. [The paper can be found here](https://www.climatechange.ai/papers/neurips2024/8). Credits to **Mathias Tobler** for frist conceptualizing the idea. | ||
|
|
||
| Key contributions to this work include [PyHa](https://github.com/UCSD-E4E/pyha), the python repository where the main techonologies used in the paper are stored. Credits primarly to **Jacob Ayers** for crediting the repo and vision for the project and **Samantha Prestrelski** for the work has done developing it and carrying out experiments. Further thanks to **Gabriel Steinberg** for his techical contributions with isolation techinques and chunking methods and **Mugen Blue** for his training TweetyNet, which was the most successful method used as seen in the paper. |
There was a problem hiding this comment.
did you intend Credits primarily to Jacob Ayers for crediting the repo to instead be Credit primarily to Jacob Ayers for creating the repo
Recommend the following:
Credits primarly to **Jacob Ayers** for crediting the repo and vision for the project and **Samantha Prestrelski** for the work has done developing it and carrying out experiments. Further thanks to **Gabriel Steinberg** for his techical contributions with isolation techinques and chunking methods and **Mugen Blue** for his training TweetyNet, which was the most successful method used as seen in the paper.
be changed to this:
Credit primarily to **Jacob Ayers** for creating the repo and for his vision of the project and **Samantha Prestrelski** for developing it and carrying out experiments. Further thanks to **Gabriel Steinberg** for his technical contributions with isolation techniques and chunking methods and **Mugen Blue** for his training of TweetyNet, which was the most successful method used as seen in the paper.
|
|
||
| Shout out to [Pyrenote](https://github.com/UCSD-E4E/Pyrenote) by **Sean Perry** for providing the the labeling for the project. | ||
|
|
||
| Last week, **Sean Perry** and **Ludwig von Schoenfeldt** attended NeurIPS 2024 and presented the work! The two traveled out of the country to Vancover, Canda to attend most of the confrence, getting to see hundreds of posters, amazing research in machine learning, and present thier own work! It was an inspiring moment getting to see where the future of the felid could be heading. |
There was a problem hiding this comment.
sp: Vancouver, Canada
sp: most of the conference
sp: see where the future of the field could be heading
|
|
||
| Last week, **Sean Perry** and **Ludwig von Schoenfeldt** attended NeurIPS 2024 and presented the work! The two traveled out of the country to Vancover, Canda to attend most of the confrence, getting to see hundreds of posters, amazing research in machine learning, and present thier own work! It was an inspiring moment getting to see where the future of the felid could be heading. | ||
|
|
||
| Acoustic Species is not done with this work. We will be continue to evalute how these methods may influnce the behavior of upstream models as we continue to work to improve bioacoustic machine learning techinques to identify species of interest. |
There was a problem hiding this comment.
sp: We will continue to evaluate how these methods
sp: may influence the behavior
| {% include | ||
| img_caption.html | ||
| src="assets/acoustic_species_id/2024_12_18_NeurIPS_North_Vancover.jpg" | ||
| caption="View of North Vancover, taken from the west side of Canda Plance looking northwest. The previous day was raining and the storm had started to move on north, appearing over the valleys of the moutains and the ski resorts. Taken by Sean Perry" |
There was a problem hiding this comment.
sp: North Vancouver
sp: Canada Place
sp: appearing over the valleys of the mountains
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.