{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ARUMOBNZHDBQL56MU4JC6H6JN5","short_pith_number":"pith:ARUMOBNZ","schema_version":"1.0","canonical_sha256":"0468c705b938c305f7cca7122f1fc96f79e5e3f3a3b514a13f23db403871c335","source":{"kind":"arxiv","id":"2507.00475","version":1},"attestation_state":"computed","paper":{"title":"AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Minoru Kishi, Ryosuke Sakai, Shinnosuke Takamichi, Yuki Okamoto, Yusuke Kanamori","submitted_at":"2025-07-01T06:46:28Z","abstract_excerpt":"We propose a novel objective evaluation metric for synthesized audio in text-to-audio (TTA), aiming to improve the performance of TTA models. In TTA, subjective evaluation of the synthesized sound is an important, but its implementation requires monetary costs. Therefore, objective evaluation such as mel-cepstral distortion are used, but the correlation between these objective metrics and subjective evaluation values is weak. Our proposed objective evaluation metric, AudioBERTScore, calculates the similarity between embedding of the synthesized and reference sounds. The method is based not onl"},"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":"2507.00475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-01T06:46:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"84e0eb2ae5be4526cce66f1b42da083cfb3d1f2ab8a40f0740bb95ae980f0f60","abstract_canon_sha256":"aca7e27973aa5cb8386f7b3c6afa6138455394d2a324f21360106f9f2b5b1fd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:09.619789Z","signature_b64":"CMXksJ13zK5qUWTUYwrl+TpgdqeNqK131k18zElTHZ1MVIXEFT1IAjSoDy4xoV9y0Bmo+CKG0XwnamWEFmtaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0468c705b938c305f7cca7122f1fc96f79e5e3f3a3b514a13f23db403871c335","last_reissued_at":"2026-07-05T11:30:09.619333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:09.619333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioBERTScore: Objective Evaluation of Environmental Sound Synthesis Based on Similarity of Audio embedding Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Minoru Kishi, Ryosuke Sakai, Shinnosuke Takamichi, Yuki Okamoto, Yusuke Kanamori","submitted_at":"2025-07-01T06:46:28Z","abstract_excerpt":"We propose a novel objective evaluation metric for synthesized audio in text-to-audio (TTA), aiming to improve the performance of TTA models. In TTA, subjective evaluation of the synthesized sound is an important, but its implementation requires monetary costs. Therefore, objective evaluation such as mel-cepstral distortion are used, but the correlation between these objective metrics and subjective evaluation values is weak. Our proposed objective evaluation metric, AudioBERTScore, calculates the similarity between embedding of the synthesized and reference sounds. The method is based not onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00475","kind":"arxiv","version":1},"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/2507.00475/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":"2507.00475","created_at":"2026-07-05T11:30:09.619386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00475v1","created_at":"2026-07-05T11:30:09.619386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00475","created_at":"2026-07-05T11:30:09.619386+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARUMOBNZHDBQ","created_at":"2026-07-05T11:30:09.619386+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARUMOBNZHDBQL56M","created_at":"2026-07-05T11:30:09.619386+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARUMOBNZ","created_at":"2026-07-05T11:30:09.619386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5","json":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5.json","graph_json":"https://pith.science/api/pith-number/ARUMOBNZHDBQL56MU4JC6H6JN5/graph.json","events_json":"https://pith.science/api/pith-number/ARUMOBNZHDBQL56MU4JC6H6JN5/events.json","paper":"https://pith.science/paper/ARUMOBNZ"},"agent_actions":{"view_html":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5","download_json":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5.json","view_paper":"https://pith.science/paper/ARUMOBNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00475&json=true","fetch_graph":"https://pith.science/api/pith-number/ARUMOBNZHDBQL56MU4JC6H6JN5/graph.json","fetch_events":"https://pith.science/api/pith-number/ARUMOBNZHDBQL56MU4JC6H6JN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5/action/storage_attestation","attest_author":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5/action/author_attestation","sign_citation":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5/action/citation_signature","submit_replication":"https://pith.science/pith/ARUMOBNZHDBQL56MU4JC6H6JN5/action/replication_record"}},"created_at":"2026-07-05T11:30:09.619386+00:00","updated_at":"2026-07-05T11:30:09.619386+00:00"}