{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QALHAX2ARO7HJMWK5IAXOHWMBQ","short_pith_number":"pith:QALHAX2A","schema_version":"1.0","canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","source":{"kind":"arxiv","id":"2409.08425","version":2},"attestation_state":"computed","paper":{"title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Helin Wang, Jiarui Hai, Karan Thakkar, Mounya Elhilali, Najim Dehak, Yen-Ju Lu","submitted_at":"2024-09-12T23:12:25Z","abstract_excerpt":"In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.08425","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T23:12:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"53fe194d438a706cdc14c261c9795aea7e5728764953cc04d929af25fc5d6194","abstract_canon_sha256":"215d0b9a7e91ee6ad80c4496115b3332fee16c5acf0c4b0b1999f3b908bd9457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:00.561731Z","signature_b64":"ysL5Pr5GL/bJv1x70+eJyU2LTMjXsPltBIM9ladjiLJKwONYq82Q40BvuxGgQzv4eO8h3Kj8EgPLiy3moph7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","last_reissued_at":"2026-07-05T09:56:00.561240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:00.561240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Helin Wang, Jiarui Hai, Karan Thakkar, Mounya Elhilali, Najim Dehak, Yen-Ju Lu","submitted_at":"2024-09-12T23:12:25Z","abstract_excerpt":"In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08425","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.08425/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.08425","created_at":"2026-07-05T09:56:00.561296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08425v2","created_at":"2026-07-05T09:56:00.561296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08425","created_at":"2026-07-05T09:56:00.561296+00:00"},{"alias_kind":"pith_short_12","alias_value":"QALHAX2ARO7H","created_at":"2026-07-05T09:56:00.561296+00:00"},{"alias_kind":"pith_short_16","alias_value":"QALHAX2ARO7HJMWK","created_at":"2026-07-05T09:56:00.561296+00:00"},{"alias_kind":"pith_short_8","alias_value":"QALHAX2A","created_at":"2026-07-05T09:56:00.561296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22106","citing_title":"AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ","json":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ.json","graph_json":"https://pith.science/api/pith-number/QALHAX2ARO7HJMWK5IAXOHWMBQ/graph.json","events_json":"https://pith.science/api/pith-number/QALHAX2ARO7HJMWK5IAXOHWMBQ/events.json","paper":"https://pith.science/paper/QALHAX2A"},"agent_actions":{"view_html":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ","download_json":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ.json","view_paper":"https://pith.science/paper/QALHAX2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08425&json=true","fetch_graph":"https://pith.science/api/pith-number/QALHAX2ARO7HJMWK5IAXOHWMBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QALHAX2ARO7HJMWK5IAXOHWMBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/action/storage_attestation","attest_author":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/action/author_attestation","sign_citation":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/action/citation_signature","submit_replication":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/action/replication_record"}},"created_at":"2026-07-05T09:56:00.561296+00:00","updated_at":"2026-07-05T09:56:00.561296+00:00"}