{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cnn-architectures-for-large-scale-audio","title":"CNN Architectures for Large-Scale Audio Classification","arxiv_id":"1609.09430","date":"2016-09-29","proceeding":null,"authors":["Shawn Hershey","Sourish Chaudhuri","Daniel P. W. Ellis","Jort F. Gemmeke","Aren Jansen","R. Channing Moore","Manoj Plakal","Devin Platt","Rif A. Saurous","Bryan Seybold","Malcolm Slaney","Ron J. Weiss","Kevin Wilson"],"abstract":"Convolutional Neural Networks (CNNs) have proven very effective in image\nclassification and show promise for audio. We use various CNN architectures to\nclassify the soundtracks of a dataset of 70M training videos (5.24 million\nhours) with 30,871 video-level labels. We examine fully connected Deep Neural\nNetworks (DNNs), AlexNet [1], VGG [2], Inception [3], and ResNet [4]. We\ninvestigate varying the size of both training set and label vocabulary, finding\nthat analogs of the CNNs used in image classification do well on our audio\nclassification task, and larger training and label sets help up to a point. A\nmodel using embeddings from these classifiers does much better than raw\nfeatures on the Audio Set [5] Acoustic Event Detection (AED) classification\ntask.","url_abs":"http://arxiv.org/abs/1609.09430v2","url_pdf":"http://arxiv.org/pdf/1609.09430v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/IBM/MAX-Audio-Classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/IBM/MAX-Audio-Embedding-Generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/biboamy/tvsm-dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/chris-lovejoy/youtube-titles-and-transcripts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/clarivando/MAX-Audio-Classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/daisukelab/sound-clf-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/deephdc/audio-classification-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/harritaylor/torchvggish","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/morrisxu-driving/video-music_cross-modal_retrival","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/nttcslab/composing-general-audio-repr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/numediart/MAFnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/semantic-search/MAX-Audio-ClassifierX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/sonycslparis/audio-metrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/stanfordmlgroup/aihc-sum20-lung-sounds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/stanfordmlgroup/selfsupervised-lungandheartsounds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"cnn-architectures-for-large-scale-audio","repo_url":"https://github.com/towhee-io/towhee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"youtube-100m","name":"YouTube-100M","full_name":"YouTube-100m"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.09430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.09430"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harritaylor/torchvggish","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordmlgroup/selfsupervised-lungandheartsounds","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/semantic-search/MAX-Audio-ClassifierX","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/biboamy/tvsm-dataset","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/morrisxu-driving/video-music_cross-modal_retrival","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chris-lovejoy/youtube-titles-and-transcripts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/clarivando/MAX-Audio-Classifier","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deephdc/audio-classification-tf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nttcslab/composing-general-audio-repr","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/numediart/MAFnet","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sonycslparis/audio-metrics","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/MAX-Audio-Classifier","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/towhee-io/towhee","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daisukelab/sound-clf-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IBM/MAX-Audio-Embedding-Generator","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordmlgroup/aihc-sum20-lung-sounds","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3f76530d9bfe10a4","entry":"frame","repo":"IBM/MAX-Audio-Embedding-Generator","repo_kind":"listed","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Embedding-Generator/blob/HEAD/core/mel_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f76530d9bfe10a4"}},{"code_sha256_prefix":"ed0ef7fc8a5f1840","entry":"periodic_hann","repo":"IBM/MAX-Audio-Embedding-Generator","repo_kind":"listed","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Embedding-Generator/blob/HEAD/core/mel_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed0ef7fc8a5f1840"}},{"code_sha256_prefix":"0f0fa853ceaa04db","entry":"stft_magnitude","repo":"IBM/MAX-Audio-Embedding-Generator","repo_kind":"listed","path":"core/mel_features.py","file_url":"https://github.com/IBM/MAX-Audio-Embedding-Generator/blob/HEAD/core/mel_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f0fa853ceaa04db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}