{"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/towards-weakly-supervised-text-to-audio","title":"Towards Weakly Supervised Text-to-Audio Grounding","arxiv_id":"2401.02584","date":"2024-01-05","proceeding":null,"authors":["Xuenan Xu","Ziyang Ma","Mengyue Wu","Kai Yu"],"abstract":"Text-to-audio grounding (TAG) task aims to predict the onsets and offsets of sound events described by natural language. This task can facilitate applications such as multimodal information retrieval. This paper focuses on weakly-supervised text-to-audio grounding (WSTAG), where frame-level annotations of sound events are unavailable, and only the caption of a whole audio clip can be utilized for training. WSTAG is superior to strongly-supervised approaches in its scalability to large audio-text datasets. Two WSTAG frameworks are studied in this paper: sentence-level and phrase-level. First, we analyze the limitations of mean pooling used in the previous WSTAG approach and investigate the effects of different pooling strategies. We then propose phrase-level WSTAG to use matching labels between audio clips and phrases for training. Advanced negative sampling strategies and self-supervision are proposed to enhance the accuracy of the weak labels and provide pseudo strong labels. Experimental results show that our system significantly outperforms the previous WSTAG SOTA. Finally, we conduct extensive experiments to analyze the effects of several factors on phrase-level WSTAG. The code and model is available at https://github.com/wsntxxn/TextToAudioGrounding.","url_abs":"https://arxiv.org/abs/2401.02584v2","url_pdf":"https://arxiv.org/pdf/2401.02584v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"towards-weakly-supervised-text-to-audio","repo_url":"https://github.com/wsntxxn/TextToAudioGrounding","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.02584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02584"}},"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/wsntxxn/TextToAudioGrounding","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":"5460977cdd07db57","entry":"cdur_block","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"models/audio_encoder.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/models/audio_encoder.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":"5460977cdd07db57"}},{"code_sha256_prefix":"2e8d19a3f0d34cce","entry":"generate_length_mask","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"audio_text_retrieval_models/utils.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/audio_text_retrieval_models/utils.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":"2e8d19a3f0d34cce"}},{"code_sha256_prefix":"b261a76a952237f0","entry":"generate_length_mask","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"models/hf_modeling_grounding.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/models/hf_modeling_grounding.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":"b261a76a952237f0"}},{"code_sha256_prefix":"a90af0ecb9210e13","entry":"max_with_lens","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"audio_text_retrieval_models/utils.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/audio_text_retrieval_models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a90af0ecb9210e13"}},{"code_sha256_prefix":"e4b4d45f6304ce08","entry":"mean_with_lens","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"audio_text_retrieval_models/utils.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/audio_text_retrieval_models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4b4d45f6304ce08"}},{"code_sha256_prefix":"1470bd170368a296","entry":"mean_with_lens","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"models/hf_modeling_grounding.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/models/hf_modeling_grounding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1470bd170368a296"}},{"code_sha256_prefix":"b5d057bb1edb644b","entry":"sum_with_lens","repo":"wsntxxn/TextToAudioGrounding","repo_kind":"official","path":"models/hf_modeling_grounding.py","file_url":"https://github.com/wsntxxn/TextToAudioGrounding/blob/HEAD/models/hf_modeling_grounding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5d057bb1edb644b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}