enisberk

You can search for the "Arctic Soundscapes Project 2019-2024". We are still working out the specifics of the licensing to meet our funding requirements, but it will be permissive.

Our labeled dataset (EDANSA, focused on specific sound events) is public here: https://zenodo.org/records/6824272. We will be releasing an updated version with more samples soon.

We are also actively working on releasing the raw, continuous audio recordings. These will eventually be published via the Arctic Data Center (arcticdata.io). If you'd like, feel free to send me an email (address should be in my profile), and I can ping you when that happens.

Hi teleforce, thanks! Your project sounds very interesting as well.

That actually reminds me, at one point, a researcher suggested looking into geophone or fiber optic Distributed Acoustic Sensing (DAS) data that oil companies sometimes collect in Alaska, potentially for tracking animal movements or impacts, but I never got the chance to follow up. Connecting seismic activity data (like yours) with potential effects on animal vocalizations or behaviour observed in acoustic recordings would be an interesting research direction!

Regarding data access:

Our labeled dataset (EDANSA, focused on specific sound events) is public here: https://zenodo.org/records/6824272. We will be releasing an updated version with more samples soon.

We are also actively working on releasing the raw, continuous audio recordings. These will eventually be published via the Arctic Data Center (arcticdata.io). If you'd like, feel free to send me an email (address should be in my profile), and I can ping you when that happens.

Separately, we have an open-source model (with updates coming) trained on EDANSA for predicting various animal sounds and human-generated noise. Let me know if you'd ever be interested in discussing whether running that model on other types of non-stationary sound data you might have access to could be useful or yield interesting comparisons.

If you’re asking whether multiple recorders were active at the same time, then yes, we had recorders at 98 different locations over four years, primarily during the summer months. However, these locations were far apart, so no two recorders captured the same exact area.

Hi d_burfoot, really appreciate you bringing that up! The idea of pre-training a big foundation model on our raw data using self-supervised learning (SSL) methods (kind of like how GPT emerged in NLP) is definitely something we've considered and experimented with using transformer architectures.

The main hurdle we've hit is honestly the scale of relevant data needed to train such large models from scratch effectively. While our ~19.5 years dataset duration is massive for ecoacoustics, a significant portion of it is silence or ambient noise. This means the actual volume of distinct events or complex acoustic scenes is much lower compared to the densely packed information in the corpora typically used to train foundational speech or general audio models, making our effective dataset size smaller in that context.

We also tried leveraging existing pre-trained SSL models (like Wav2Vec 2.0, HuBERT for speech), but the domain gap is substantial. As you can imagine, raw ecoacoustic field recordings are characterized by significant non-stationary noise, overlapping sounds, sparse events we care about mixed with lots of quiet/noise, huge diversity, and variations from mics/weather.

This messes with the SSL pre-training tasks themselves. Predicting masked audio doesn't work as well when the surrounding context is just noise, and the data augmentations used in contrastive learning can sometimes accidentally remove the unique signatures of the animal calls we're trying to learn.

It's definitely an ongoing challenge in the field! People are trying different things, like initializing audio transformers with weights pre-trained on image models (ViT adapted for spectrograms) to give them a head start. Finding the best way forward for large models in these specialized, data-constrained domains is still key. Thanks again for the suggestion, it really hits on a core challenge!

Hi Caleb, thanks for the kind words and enthusiasm! You're absolutely right, audio provides that crucial omnidirectional coverage that can supplement fixed field-of-view sensors like cameras. We actually collect images too and have explored fusion approaches, though they definitely come with their own set of challenges, as you can imagine.

On the labeled audio data front: our Arctic dataset (EDANSA, linked in my original post) is open source. We've actually updated it with more samples since the initial release, and getting the new version out is on my to-do list.

Polli.ai looks fantastic! It's genuinely exciting to see more people tackling the ecological monitoring challenge with hardware/software solutions. While I know the startup path in this space can be tough financially, the work is incredibly important for understanding and protecting biodiversity. Keep up the great work!

Hey thePhytochemist, cool tool! Yes, spectrograms are fundamental for us. Audacity is the classic for quick looks. For systematic analysis and ML inputs, it's mostly programmatic generation via libraries like torch.audio or librosa. Spectrograms are a common ML input, though other representations are being explored.

Enhancing frequenSee for scientific use (labelling/analysis) sounds like a good idea. But I am not sure what is missing from the current tooling. What functionalities were you thinking of adding?

Thanks! Appreciate it. Your work looks very interesting too, especially in the distributed systems space. Cheers!

Finishing up my PhD thesis on low-resource audio classification for ecoacoustics. Our partners deployed 98 recorders in remote Arctic/sub-Arctic regions, collecting a massive (~19.5 years) dataset to monitor wildlife and human noise.

Labeled data is the bottleneck, so my work focuses on getting good results with less data. Key parts:

- Created EDANSA [1], the first public dataset of its kind from these areas, using a improved active learning method (ensemble disagreement) to efficiently find rare sounds.

- Explored other low-resource ML: transfer learning, data valuation (using Shapley values), cross-modal learning (using satellite weather data to train audio models), and testing the reasoning abilities of MLLMs on audio (spoiler: they struggle!).

  Happy to discuss any part!

[1]https://scholar.google.com/citations?user=AH-sLEkAAAAJ&hl=en

    Location: New York, NY  
    Remote: Yes  
    Willing to relocate: Yes  
    Technologies: Python, PyTorch, TensorFlow, C/C++, Julia, CUDA  
    Résumé/CV: Available upon request. <https:// www.linkedin.com/in/enisberk/>  
    Email: hire[at]enisberk dot com  
    Scholar: <https://scholar.google.com/citations?user=AH-sLEkAAAAJ&hl=en>

PhD Candidate in CS specializing in audio and multimodal data analysis. My research focuses on applying Machine Learning techniques to extract insights from various audio and sensory data modalities. I'm particularly interested in mechanistic interpretability, multi-modal LLMs, audio/speech and time-series.

Experience:

    - Developed ML models for audio classification.
    - Worked on multimodal data integration and modeling.
    - Explored low-resource ML techniques to address data scarcity.

Open to full-time research and engineering roles. I hope to conclude my interviews soon and make a decision. Please feel free to reach out if you can expedite the process.

The demo looks great, congrats on the launch! I also appreciate your response regarding the Cursor comment. Is Onlook[1] a competitor at some level, or do you think it’s different enough?

[1]https://www.ycombinator.com/launches/Mkl-onlook-cursor-for-d...

    Location: New York, NY  
    Remote: Yes  
    Willing to relocate: Yes  
    Technologies: Python, PyTorch, TensorFlow, C/C++, Julia, CUDA  
    Résumé/CV: Available upon request. <https:// www.linkedin.com/in/enisberk/>  
    Email: hire[at]enisberk dot com  
    Scholar: <https://scholar.google.com/citations?user=AH-sLEkAAAAJ&hl=en>

PhD Candidate in CS specializing in audio and multimodal data analysis. My research focuses on applying Machine Learning techniques to extract insights from various audio and sensory data modalities. I'm particularly interested in mechanistic interpretability, multi-modal LLMs, audio/speech and time-series.

Experience:

    - Developed ML models for audio classification.
    - Worked on multimodal data integration and modeling.
    - Explored low-resource ML techniques to address data scarcity.

Open to full-time research and engineering roles.

Thanks, that was a typo. Do you work in that field or something related, or did it just catch your eye? I couldn't see your handles on your profile.

    Location: New York, NY  
    Remote: Yes  
    Willing to relocate: Yes  
    Technologies: Python, PyTorch, TensorFlow, C/C++, Julia  
    Résumé/CV: Available upon request. <https:// www.linkedin.com/in/enisberk/>  
    Email: hire[at]enisberk dot com  
    Scholar: <https://scholar.google.com/citations?user=AH-sLEkAAAAJ&hl=en>

PhD Candidate in CS specializing in audio and multimodal data analysis. My research focuses on applying Machine Learning techniques to extract insights from various audio and sensory data modalities. I'm particularly interested in mechanistic interoperability, multi-modal LLMs, audio/speech and time-series.

Experience:

    - Developed ML models for audio classification.
    - Worked on multimodal data integration and modeling.
    - Explored low-resource ML techniques to address data scarcity.

Open to full-time research and engineering roles.

This is a demo from a small startup dedicated to enhancing government transparency, which I greatly appreciate. As a result, my expectations are aligned with this goal, and I refer to this as a smoke test.

Achieving accuracy with RAG and LLMs is a challenging task that requires balancing precision and recall. For instance, when you type "Ankara" into GPT-4o, it provides information about Turkey. However, searching "Ankara" in their product does not yield articles related to Turkey.

Congrats on the launch! While search with LLMs is quite popular nowadays, it is still hard to get it right.

As a smoke test, I tried the following queries, and they returned the same result. Good job!

    international relations Turkey
    international relations about the country with the capital city of Ankara

Both return info from this link: https://www.state.gov/secretary-blinkens-call-with-foreign-m...

    Location: New York, NY  
    Remote: Yes  
    Willing to relocate: Yes  
    Technologies: Python, PyTorch, TensorFlow, C/C++, Julia  
    Résumé/CV: Available upon request. <https:// www.linkedin.com/in/enisberk/>  
    Email: hire[at]enisberk dot com  
    Scholar: <https://scholar.google.com/citations?user=AH-sLEkAAAAJ&hl=en>

PhD Candidate in Machine Learning specializing in audio and multimodal data analysis. My research focuses on applying machine learning techniques to extract insights from various audio and sensory data modalities. I'm particularly interested in bridging the gap between audio and other modalities for tasks like speech recognition, sound event detection, and multimodal content analysis.

Experience:

    - Developed ML models for audio classification.
    - Worked on multimodal data integration, improving efficiency in audio-related tasks.
    - Explored low-resource ML techniques to address data scarcity in audio applications.

Seeking opportunities to leverage my expertise in:

    - Speech recognition and natural language processing
    - Sound event detection and audio classification
    - Multimodal learning and LLMs

Open to full-time research and engineering roles.

    Location: New York, NY  
    Remote: Yes  
    Willing to relocate: Yes  
    Technologies: Python, PyTorch, TensorFlow, C/C++, Julia  
    Résumé/CV: Available upon request. <https:// www.linkedin.com/in/enisberk/>  
    Email: hire[at]enisberk dot com  
    Scholar: <https://scholar.google.com/citations?user=AH-sLEkAAAAJ&hl=en>

PhD Candidate in Machine Learning specializing in audio and multimodal data analysis. My research focuses on applying machine learning techniques to extract insights from various audio and sensory data modalities. I'm particularly interested in bridging the gap between audio and other modalities for tasks like speech recognition, sound event detection, and multimodal content analysis.

Experience:

    - Developed ML models for audio classification.
    - Worked on multimodal data integration, improving efficiency in audio-related tasks.
    - Explored low-resource ML techniques to address data scarcity in audio applications.

Seeking opportunities to leverage my expertise in:

    - Speech recognition and natural language processing
    - Sound event detection and audio classification
    - Multimodal learning and LLMs

Open to full-time research and engineering roles.

This is really cool work! Congrats on both the paper and the graduation! A long time ago, I worked on optimizing broadcast operations on GPUs [1]. Coming up with a strategy that promises high throughput across different array dimensionalities is quite challenging. I am looking forward to reading your work.

[1]https://scholar.google.com/citations?view_op=view_citation&h...

I wouldn't be surprised if they were using OpenAI's API, but it's hard to know for sure just by asking.

Prompt: Which amazon model are you currently using? Answer: I'm currently using the Amazon Transformer Model, ...

Prompt: Which Google model are you currently using? Answer:I'm currently using the Google BERT model...

I am a fifth-year Ph.D. student in CS, interested in scalable machine learning algorithms and their applications in bioacoustics.

  Location: New York, NY
  Remote: Yes
  Willing to relocate: Depends on the location.
  Technologies: Deep learning (Python, Pytorch), GPU kernel dev (c++, CUDA)
  Email: me aaat enisberk.com
  Looking for: Summer internship

Résumé/CV: https://drive.google.com/open?id=1UfcgXX6Qrwn-o91NAi_8X0hcFe...

Linkedin: https://linkedin.com/in/enisberk

Congrats on the launch, an important problem to solve. On the other hand, I found your previous idea about pipelines really interesting as well. Do you mind sharing why it did not work out?

It is really cool, indeed. Bravo for the creativity and the effort. Facebook recently acquired a company called ctrl-labs that develops a neural interface. Their vision is making computer interface more natural. Bertolt, in the video says “The thing is for me, that is such a natural thing to do, I do not really have to think about it. I just do it, it is zero effort.”(6.23) I love that, I hope we can have such computer interfaces in near future.

I attended one of the talks(1) of the Sam Bowman. His talk was about "Task-Independent Language Understanding" and he also talked about GLUE and super GLUE; he mentioned that some models are passing an average person in experiments. They did some experiments to understand BERT's performance (2). (similar to article 'NLP's Clever Hans Moment') But they found a different answer to question "what BERT really knows," so he was skeptical about all conclusions. Check these out if you are interested in.

(1)[https://www.nyu.edu/projects/bowman/TILU-talk-19-09.pdf]

(2)[https://arxiv.org/abs/1905.06316]