{"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/coala-co-aligned-autoencoders-for-learning","title":"COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations","arxiv_id":"2006.08386","date":"2020-06-15","proceeding":null,"authors":["Xavier Favory","Konstantinos Drossos","Tuomas Virtanen","Xavier Serra"],"abstract":"Audio representation learning based on deep neural networks (DNNs) emerged as an alternative approach to hand-crafted features. For achieving high performance, DNNs often need a large amount of annotated data which can be difficult and costly to obtain. In this paper, we propose a method for learning audio representations, aligning the learned latent representations of audio and associated tags. Aligning is done by maximizing the agreement of the latent representations of audio and tags, using a contrastive loss. The result is an audio embedding model which reflects acoustic and semantic characteristics of sounds. We evaluate the quality of our embedding model, measuring its performance as a feature extractor on three different tasks (namely, sound event recognition, and music genre and musical instrument classification), and investigate what type of characteristics the model captures. Our results are promising, sometimes in par with the state-of-the-art in the considered tasks and the embeddings produced with our method are well correlated with some acoustic descriptors.","url_abs":"https://arxiv.org/abs/2006.08386v2","url_pdf":"https://arxiv.org/pdf/2006.08386v2.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":"coala-co-aligned-autoencoders-for-learning","repo_url":"https://github.com/xavierfav/coala","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"coala-co-aligned-autoencoders-for-learning","repo_url":"https://github.com/yijerjer/music_genre_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.08386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08386"}},"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/yijerjer/music_genre_classification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xavierfav/coala","reach":null}],"summary":{"ran":3,"ran_fixture":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1},"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"a60af54cdf63b14b","entry":"ConvBlock","repo":"yijerjer/music_genre_classification","repo_kind":"listed","path":"cnn_models.py","file_url":"https://github.com/yijerjer/music_genre_classification/blob/HEAD/cnn_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a60af54cdf63b14b"}},{"code_sha256_prefix":"ecc9d811b5842de5","entry":"DualAETrainer","repo":"xavierfav/coala","repo_kind":"official","path":"dual_ae_trainer.py","file_url":"https://github.com/xavierfav/coala/blob/HEAD/dual_ae_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ecc9d811b5842de5"}},{"code_sha256_prefix":"a249acfa9e68f2eb","entry":"InMemoryDataset","repo":"xavierfav/coala","repo_kind":"official","path":"dual_ae_trainer.py","file_url":"https://github.com/xavierfav/coala/blob/HEAD/dual_ae_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a249acfa9e68f2eb"}},{"code_sha256_prefix":"7567a11b33565b39","entry":"contrastive_loss","repo":"xavierfav/coala","repo_kind":"official","path":"dual_ae_trainer.py","file_url":"https://github.com/xavierfav/coala/blob/HEAD/dual_ae_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7567a11b33565b39"}},{"code_sha256_prefix":"99a215366b6ba1c1","entry":"embeddings_to_cosine_similarity_matrix","repo":"xavierfav/coala","repo_kind":"official","path":"dual_ae_trainer.py","file_url":"https://github.com/xavierfav/coala/blob/HEAD/dual_ae_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99a215366b6ba1c1"}},{"code_sha256_prefix":"51b431bae9caa13e","entry":"kullback_leibler","repo":"xavierfav/coala","repo_kind":"official","path":"dual_ae_trainer.py","file_url":"https://github.com/xavierfav/coala/blob/HEAD/dual_ae_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51b431bae9caa13e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}