Hi everyone ! Looking through the literature, I fell on those previous works that could help you get started.
\n\nFirst of all, on Kaggle, you have a lot of interesting notebooks, competitions or datasets to get started : \n- https://www.kaggle.com/mmoreaux/environmental-sound-classification-50\n- https://www.kaggle.com/c/freesound-audio-tagging/data\n- https://www.kaggle.com/devilsknight/sound-classification-using-spectrogram-images\n- https://www.kaggle.com/mychen76/automatic-urban-sound-classification-with-cnn\n- https://www.kaggle.com/ashishpatel26/feature-extraction-from-audio\n- https://www.kaggle.com/fizzbuzz/beginner-s-guide-to-audio-data
\n\nMore generally, on sound classification using deep learning : \n- a very complete review of literature\n- @mikesmales/sound-classification-using-deep-learning-8bc2aa1990b7\">The basics, on medium\n- a wide library of available papers here\n- if you like tensorflow\n\n- ... or if you're more of a torch person : here and here\n- an interesting idea with [Deep Generative Architectures](Deep Generative Architectures)
\n\nMore specifically, on bird sound classification : \n- Women in machine learning and Data Science project (girls rule 🙌 )\n- on CEUR you have 2 different works with CNN : one from 2017 and one from 2019\n- using more handcrafted features, but still CNN : this one on australian birds\n- kernel-based machine learning\n- still CNN, on researchGate, you have this one and this one\n- if you feel allergic to handcrafted features or magic, you have this paper on arxiv\n\n- that very innovative one using transfer learning, still on arxiv
\n\nIf you have, like me, a special interest to Generative Adversarial Networks & DeepGANs:\n- towardsdatascience, of course\n- for data augmentation : environmental sounds classification\n- masked CNN (bit out of topic, but didn't know where to put it)\n- audio generation with GAN\n- Unsupervised Feature Learning for Environmental Sound Classification Using Cycle Consistent Generative Adversarial Network\n- still data augmentation with GAN\n
\n\n... my conclusion ? Well, CNN seems to be a good place to start (at least, very widely used in the literature). You have sample codes from a lot of papers available online, for example here for the paper Large-Scale Bird Sound Classification using\nConvolutional Neural Networks. But don't get stuck at reproducing peer-reviewed literature ! Try new things, and happy kaggling !
", "messages": [ { "id": "887712", "postDate": "06/15/2020 20:15:59", "content": "Hi everyone ! Looking through the literature, I fell on those previous works that could help you get started.
\n\nFirst of all, on Kaggle, you have a lot of interesting notebooks, competitions or datasets to get started : \n- https://www.kaggle.com/mmoreaux/environmental-sound-classification-50\n- https://www.kaggle.com/c/freesound-audio-tagging/data\n- https://www.kaggle.com/devilsknight/sound-classification-using-spectrogram-images\n- https://www.kaggle.com/mychen76/automatic-urban-sound-classification-with-cnn\n- https://www.kaggle.com/ashishpatel26/feature-extraction-from-audio\n- https://www.kaggle.com/fizzbuzz/beginner-s-guide-to-audio-data
\n\nMore generally, on sound classification using deep learning : \n- a very complete review of literature\n- @mikesmales/sound-classification-using-deep-learning-8bc2aa1990b7\">The basics, on medium\n- a wide library of available papers here\n- if you like tensorflow\n\n- ... or if you're more of a torch person : here and here\n- an interesting idea with [Deep Generative Architectures](Deep Generative Architectures)
\n\nMore specifically, on bird sound classification : \n- Women in machine learning and Data Science project (girls rule 🙌 )\n- on CEUR you have 2 different works with CNN : one from 2017 and one from 2019\n- using more handcrafted features, but still CNN : this one on australian birds\n- kernel-based machine learning\n- still CNN, on researchGate, you have this one and this one\n- if you feel allergic to handcrafted features or magic, you have this paper on arxiv\n\n- that very innovative one using transfer learning, still on arxiv
\n\nIf you have, like me, a special interest to Generative Adversarial Networks & DeepGANs:\n- towardsdatascience, of course\n- for data augmentation : environmental sounds classification\n- masked CNN (bit out of topic, but didn't know where to put it)\n- audio generation with GAN\n- Unsupervised Feature Learning for Environmental Sound Classification Using Cycle Consistent Generative Adversarial Network\n- still data augmentation with GAN\n
\n\n... my conclusion ? Well, CNN seems to be a good place to start (at least, very widely used in the literature). You have sample codes from a lot of papers available online, for example here for the paper Large-Scale Bird Sound Classification using\nConvolutional Neural Networks. But don't get stuck at reproducing peer-reviewed literature ! Try new things, and happy kaggling !
", "rawMarkdown": "Hi everyone ! Looking through the literature, I fell on those previous works that could help you get started.\n\nFirst of all, on Kaggle, you have a lot of interesting notebooks, competitions or datasets to get started : \n- https://www.kaggle.com/mmoreaux/environmental-sound-classification-50\n- https://www.kaggle.com/c/freesound-audio-tagging/data\n- https://www.kaggle.com/devilsknight/sound-classification-using-spectrogram-images\n- https://www.kaggle.com/mychen76/automatic-urban-sound-classification-with-cnn\n- https://www.kaggle.com/ashishpatel26/feature-extraction-from-audio\n- https://www.kaggle.com/fizzbuzz/beginner-s-guide-to-audio-data\n\nMore generally, on **sound classification using deep learning** : \n- a very complete [review of literature](https://www.mdpi.com/2076-3417/10/6/2020/pdf)\n- [The basics, on medium](https://medium.com/@mikesmales/sound-classification-using-deep-learning-8bc2aa1990b7)\n- a wide library of available papers [here](https://paperswithcode.com/task/audio-classification)\n- [if you like tensorflow\n](https://www.iotforall.com/tensorflow-sound-classification-machine-learning-applications/)\n- ... or if you're more of a torch person : [here](https://pytorch.org/tutorials/beginner/audio_classifier_tutorial.html?highlight=audio) and [here](https://medium.com/@hasithsura/audio-classification-d37a82d6715)\n- an interesting idea with [Deep Generative Architectures](Deep Generative Architectures)\n\nMore specifically, on **bird sound classification** : \n- [Women in machine learning and Data Science](https://towardsdatascience.com/sound-based-bird-classification-965d0ecacb2b) project (girls rule 🙌 )\n- on CEUR you have 2 different works with CNN : [one from 2017](http://ceur-ws.org/Vol-1866/paper_143.pdf) and [one from 2019](http://ceur-ws.org/Vol-2380/paper_68.pdf)\n- using more handcrafted features, but still CNN : [this one on australian birds](https://www.sciencedirect.com/science/article/abs/pii/S1574954118302991)\n- [kernel-based machine learning](https://asa.scitation.org/doi/10.1121/1.5004570)\n- still CNN, on researchGate, you have [this one](https://www.researchgate.net/publication/328836649_Bird_Sound_Recognition_Using_a_Convolutional_Neural_Network) and [this one](https://www.researchgate.net/publication/322144806_Large-Scale_Bird_Sound_Classification_using_Convolutional_Neural_Networks)\n- if you feel allergic to handcrafted features or magic, you have [this paper on arxiv\n](https://arxiv.org/pdf/1807.05812.pdf)\n- [that very innovative one](https://arxiv.org/ftp/arxiv/papers/1803/1803.01107.pdf) using transfer learning, still on arxiv\n\nIf you have, like me, a special interest to Generative Adversarial Networks & DeepGANs:\n- [towardsdatascience](https://towardsdatascience.com/synthesizing-audio-with-generative-adversarial-networks-8e0308184edd), of course\n- for data augmentation : [environmental sounds classification](https://ieeexplore.ieee.org/document/8902819)\n- [masked CNN](https://www.sciencedirect.com/science/article/pii/S1568494620300132) (bit out of topic, but didn't know where to put it)\n- [audio generation with GAN](https://medium.com/neuronio/audio-generation-with-gans-428bc2de5a89)\n- [Unsupervised Feature Learning for Environmental Sound Classification Using Cycle Consistent Generative Adversarial Network](https://www.groundai.com/project/unsupervised-feature-learning-for-environmental-sound-classification-using-cycle-consistent-generative-adversarial-network/1)\n- still [data augmentation with GAN\n](https://www.researchgate.net/publication/335739623_Data_Augmentation_Using_Generative_Adversarial_Network_for_Environmental_Sound_Classification)\n\n... my conclusion ? Well, CNN seems to be a good place to start (at least, very widely used in the literature). You have sample codes from a lot of papers available online, for example [here](https://github.com/kahst/BirdCLEF2017) for the paper [Large-Scale Bird Sound Classification using\nConvolutional Neural Networks](http://ceur-ws.org/Vol-1866/paper_143.pdf). But don't get stuck at reproducing peer-reviewed literature ! Try new things, and happy kaggling !", "votes": null }, { "id": "887902", "postDate": "06/16/2020 01:46:16", "content": "I found a project of bird calls classification.\nhttps://github.com/Mipanox/Bird_cocktail
", "rawMarkdown": "I found a project of bird calls classification.\nhttps://github.com/Mipanox/Bird_cocktail", "votes": null }, { "id": "888206", "postDate": "06/16/2020 07:31:44", "content": "Thanks for this nice list @louise2001
\n\nI'd like to add two resources from the 2018/2019 BirdCLEF competition:
\n\nThis is a great list @louise2001!
", "rawMarkdown": "This is a great list @louise2001!", "votes": null }, { "id": "891582", "postDate": "06/18/2020 09:19:30", "content": "Thanks for sharing, greatly helpful.
", "rawMarkdown": "Thanks for sharing, greatly helpful.", "votes": null }, { "id": "893219", "postDate": "06/19/2020 13:16:16", "content": "@louise2001 solid gold. Thank you for this great list. :)
", "rawMarkdown": "louise2001 solid gold. Thank you for this great list. :)", "votes": null }, { "id": "894162", "postDate": "06/20/2020 07:50:39", "content": "good one
", "rawMarkdown": "good one", "votes": null }, { "id": "896091", "postDate": "06/21/2020 20:18:40", "content": "Thanksss!! 💙
", "rawMarkdown": "Thanksss!! 💙", "votes": null }, { "id": "898638", "postDate": "06/23/2020 16:39:18", "content": "add one more Urban Sound Classification blog
", "rawMarkdown": "add one more [Urban Sound Classification blog](http://aqibsaeed.github.io/2016-09-03-urban-sound-classification-part-1/)", "votes": null }, { "id": "902706", "postDate": "06/26/2020 10:06:59", "content": "Thanks for sharing. They are definitely going to be very helpful. Keep up the good work 👍
\n\nDo check out and review my notebook on Audio feature analysis. Thank you.
", "rawMarkdown": "Thanks for sharing. They are definitely going to be very helpful. Keep up the good work 👍\n \nDo check out and review [my notebook on Audio feature analysis](https://www.kaggle.com/navinmundhra/cornell-birdcall-extensive-eda-fe). Thank you.", "votes": null }, { "id": "904705", "postDate": "06/27/2020 20:29:29", "content": "@louise2001 That's informative! Thankyou for sharing.
", "rawMarkdown": "louise2001 That's informative! Thankyou for sharing.", "votes": null }, { "id": "907440", "postDate": "06/30/2020 00:57:58", "content": "Fantastic work! I added this page to my literature review page - https://www.kaggle.com/c/birdsong-recognition/discussion/162688 . Also appreciate your efforts using data science for green-financing and for good.
", "rawMarkdown": "Fantastic work! I added this page to my literature review page - https://www.kaggle.com/c/birdsong-recognition/discussion/162688 . Also appreciate your efforts using data science for green-financing and for good.", "votes": null }, { "id": "912083", "postDate": "07/02/2020 07:54:37", "content": "", "rawMarkdown": "[Overview of BirdCLEF 2019](http://ceur-ws.org/Vol-2380/paper_256.pdf)", "votes": null }, { "id": "962103", "postDate": "08/07/2020 20:07:11", "content": "Wow, thanks!!!
\n\n\nan interesting idea with [Deep Generative Architectures](Deep Generative Architectures)
\n
missing link?
", "rawMarkdown": "Wow, thanks!!!\n\n> an interesting idea with [Deep Generative Architectures](Deep Generative Architectures)\n\nmissing link?", "votes": null }, { "id": "966912", "postDate": "08/11/2020 18:48:03", "content": "\n\n… or if you're more of a torch person : here
\n
Seems the runnable code has been removed :'(
", "rawMarkdown": "> … or if you're more of a torch person : here\n\nSeems the runnable code has been removed :'(", "votes": null }, { "id": "1260846", "postDate": "04/02/2021 13:02:24", "content": "16GB Xeno-Canto Bird Recordings Dataset:
\nhttps://www.kaggle.com/imoore/xenocanto-bird-recordings-dataset
Wow, thanks!!!
\n\n\nan interesting idea with [Deep Generative Architectures](Deep Generative Architectures)
\n
missing link?
", "votes": null, "replies": [] }, { "id": 966912, "author_name": "marcogorelli", "author_url": "", "post_date": "08/11/2020 18:48:03", "content": "\n\n… or if you're more of a torch person : here
\n
Seems the runnable code has been removed :'(
", "votes": null, "replies": [] }, { "id": 1260846, "author_name": "andrey136", "author_url": "", "post_date": "04/02/2021 13:02:24", "content": "16GB Xeno-Canto Bird Recordings Dataset:
\nhttps://www.kaggle.com/imoore/xenocanto-bird-recordings-dataset
I found a project of bird calls classification.\nhttps://github.com/Mipanox/Bird_cocktail
", "votes": null, "replies": [] }, { "id": 888206, "author_name": "stefankahl", "author_url": "", "post_date": "06/16/2020 07:31:44", "content": "Thanks for this nice list @louise2001
\n\nI'd like to add two resources from the 2018/2019 BirdCLEF competition:
\n\nThis is a great list @louise2001!
", "votes": null, "replies": [] }, { "id": 891582, "author_name": "jiegeng94", "author_url": "", "post_date": "06/18/2020 09:19:30", "content": "Thanks for sharing, greatly helpful.
", "votes": null, "replies": [] }, { "id": 893219, "author_name": "crained", "author_url": "", "post_date": "06/19/2020 13:16:16", "content": "@louise2001 solid gold. Thank you for this great list. :)
", "votes": null, "replies": [] }, { "id": 894162, "author_name": "muralidhar123", "author_url": "", "post_date": "06/20/2020 07:50:39", "content": "good one
", "votes": null, "replies": [] }, { "id": 896091, "author_name": "hugopassos", "author_url": "", "post_date": "06/21/2020 20:18:40", "content": "Thanksss!! 💙
", "votes": null, "replies": [] }, { "id": 898638, "author_name": "mlneo07", "author_url": "", "post_date": "06/23/2020 16:39:18", "content": "add one more Urban Sound Classification blog
", "votes": null, "replies": [] }, { "id": 902706, "author_name": "navinmundhra", "author_url": "", "post_date": "06/26/2020 10:06:59", "content": "Thanks for sharing. They are definitely going to be very helpful. Keep up the good work 👍
\n\nDo check out and review my notebook on Audio feature analysis. Thank you.
", "votes": null, "replies": [] }, { "id": 904705, "author_name": "dhruvagg", "author_url": "", "post_date": "06/27/2020 20:29:29", "content": "@louise2001 That's informative! Thankyou for sharing.
", "votes": null, "replies": [] }, { "id": 907440, "author_name": "tpmeli", "author_url": "", "post_date": "06/30/2020 00:57:58", "content": "Fantastic work! I added this page to my literature review page - https://www.kaggle.com/c/birdsong-recognition/discussion/162688 . Also appreciate your efforts using data science for green-financing and for good.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "887712": "Hi everyone ! Looking through the literature, I fell on those previous works that could help you get started.\n\nFirst of all, on Kaggle, you have a lot of interesting notebooks, competitions or datasets to get started : \n- https://www.kaggle.com/mmoreaux/environmental-sound-classification-50\n- https://www.kaggle.com/c/freesound-audio-tagging/data\n- https://www.kaggle.com/devilsknight/sound-classification-using-spectrogram-images\n- https://www.kaggle.com/mychen76/automatic-urban-sound-classification-with-cnn\n- https://www.kaggle.com/ashishpatel26/feature-extraction-from-audio\n- https://www.kaggle.com/fizzbuzz/beginner-s-guide-to-audio-data\n\nMore generally, on **sound classification using deep learning** : \n- a very complete [review of literature](https://www.mdpi.com/2076-3417/10/6/2020/pdf)\n- [The basics, on medium](https://medium.com/@mikesmales/sound-classification-using-deep-learning-8bc2aa1990b7)\n- a wide library of available papers [here](https://paperswithcode.com/task/audio-classification)\n- [if you like tensorflow\n](https://www.iotforall.com/tensorflow-sound-classification-machine-learning-applications/)\n- ... or if you're more of a torch person : [here](https://pytorch.org/tutorials/beginner/audio_classifier_tutorial.html?highlight=audio) and [here](https://medium.com/@hasithsura/audio-classification-d37a82d6715)\n- an interesting idea with [Deep Generative Architectures](Deep Generative Architectures)\n\nMore specifically, on **bird sound classification** : \n- [Women in machine learning and Data Science](https://towardsdatascience.com/sound-based-bird-classification-965d0ecacb2b) project (girls rule 🙌 )\n- on CEUR you have 2 different works with CNN : [one from 2017](http://ceur-ws.org/Vol-1866/paper_143.pdf) and [one from 2019](http://ceur-ws.org/Vol-2380/paper_68.pdf)\n- using more handcrafted features, but still CNN : [this one on australian birds](https://www.sciencedirect.com/science/article/abs/pii/S1574954118302991)\n- [kernel-based machine learning](https://asa.scitation.org/doi/10.1121/1.5004570)\n- still CNN, on researchGate, you have [this one](https://www.researchgate.net/publication/328836649_Bird_Sound_Recognition_Using_a_Convolutional_Neural_Network) and [this one](https://www.researchgate.net/publication/322144806_Large-Scale_Bird_Sound_Classification_using_Convolutional_Neural_Networks)\n- if you feel allergic to handcrafted features or magic, you have [this paper on arxiv\n](https://arxiv.org/pdf/1807.05812.pdf)\n- [that very innovative one](https://arxiv.org/ftp/arxiv/papers/1803/1803.01107.pdf) using transfer learning, still on arxiv\n\nIf you have, like me, a special interest to Generative Adversarial Networks & DeepGANs:\n- [towardsdatascience](https://towardsdatascience.com/synthesizing-audio-with-generative-adversarial-networks-8e0308184edd), of course\n- for data augmentation : [environmental sounds classification](https://ieeexplore.ieee.org/document/8902819)\n- [masked CNN](https://www.sciencedirect.com/science/article/pii/S1568494620300132) (bit out of topic, but didn't know where to put it)\n- [audio generation with GAN](https://medium.com/neuronio/audio-generation-with-gans-428bc2de5a89)\n- [Unsupervised Feature Learning for Environmental Sound Classification Using Cycle Consistent Generative Adversarial Network](https://www.groundai.com/project/unsupervised-feature-learning-for-environmental-sound-classification-using-cycle-consistent-generative-adversarial-network/1)\n- still [data augmentation with GAN\n](https://www.researchgate.net/publication/335739623_Data_Augmentation_Using_Generative_Adversarial_Network_for_Environmental_Sound_Classification)\n\n... my conclusion ? Well, CNN seems to be a good place to start (at least, very widely used in the literature). You have sample codes from a lot of papers available online, for example [here](https://github.com/kahst/BirdCLEF2017) for the paper [Large-Scale Bird Sound Classification using\nConvolutional Neural Networks](http://ceur-ws.org/Vol-1866/paper_143.pdf). But don't get stuck at reproducing peer-reviewed literature ! Try new things, and happy kaggling !", "887902": "I found a project of bird calls classification.\nhttps://github.com/Mipanox/Bird_cocktail", "888206": "Thanks for this nice list @louise2001 \n\nI'd like to add two resources from the 2018/2019 BirdCLEF competition:\n\n- one paper by Jan Schlüter: [http://ceur-ws.org/Vol-2125/paper_181.pdf](http://ceur-ws.org/Vol-2125/paper_181.pdf) which also has a repository: https://github.com/f0k/birdclef2018\n- and one paper by Mario Lasseck: [http://ceur-ws.org/Vol-2380/paper_86.pdf](http://ceur-ws.org/Vol-2380/paper_86.pdf) who describes one of the most sophisticated augmentation schemes", "891267": "This is a great list @louise2001!", "891582": "Thanks for sharing, greatly helpful.", "893219": "louise2001 solid gold. Thank you for this great list. :)", "894162": "good one", "896091": "Thanksss!! 💙", "898638": "add one more [Urban Sound Classification blog](http://aqibsaeed.github.io/2016-09-03-urban-sound-classification-part-1/)", "902706": "Thanks for sharing. They are definitely going to be very helpful. Keep up the good work 👍\n \nDo check out and review [my notebook on Audio feature analysis](https://www.kaggle.com/navinmundhra/cornell-birdcall-extensive-eda-fe). Thank you.", "904705": "louise2001 That's informative! Thankyou for sharing.", "907440": "Fantastic work! I added this page to my literature review page - https://www.kaggle.com/c/birdsong-recognition/discussion/162688 . Also appreciate your efforts using data science for green-financing and for good.", "912083": "[Overview of BirdCLEF 2019](http://ceur-ws.org/Vol-2380/paper_256.pdf)", "962103": "Wow, thanks!!!\n\n> an interesting idea with [Deep Generative Architectures](Deep Generative Architectures)\n\nmissing link?", "966912": "> … or if you're more of a torch person : here\n\nSeems the runnable code has been removed :'(", "1260846": "16GB Xeno-Canto Bird Recordings Dataset:\nhttps://www.kaggle.com/imoore/xenocanto-bird-recordings-dataset" }, "source": "meta" }