{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YGM4FTSC6GTH46KIQHYDFRTSLX","short_pith_number":"pith:YGM4FTSC","schema_version":"1.0","canonical_sha256":"c199c2ce42f1a67e794881f032c6725ddaaab5e0e2d368530d9408a8c0402642","source":{"kind":"arxiv","id":"2505.24571","version":1},"attestation_state":"computed","paper":{"title":"Identifying Primary Stress Across Related Languages and Dialects with Transformer-based Speech Encoder Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ivan Porupski, Nikola Ljube\\v{s}i\\'c, Peter Rupnik","submitted_at":"2025-05-30T13:23:46Z","abstract_excerpt":"Automating primary stress identification has been an active research field due to the role of stress in encoding meaning and aiding speech comprehension. Previous studies relied mainly on traditional acoustic features and English datasets. In this paper, we investigate the approach of fine-tuning a pre-trained transformer model with an audio frame classification head. Our experiments use a new Croatian training dataset, with test sets in Croatian, Serbian, the Chakavian dialect, and Slovenian. By comparing an SVM classifier using traditional acoustic features with the fine-tuned speech transfo"},"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":"2505.24571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-30T13:23:46Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"1fbb095d53cc0718f89ffeb7cd64e53df31ddf6bcf3f9b9a5b51649cb57e4acf","abstract_canon_sha256":"5e8352fd65407400f891505fb5003355f98bd6d0f77e9d4c60c0678d92cf08e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:52.444675Z","signature_b64":"oSjddwVA8tZiXQVulxPLd/uQdrIHD0SXBpFVVu692SFbzIOpWoqw8tf5GW7wHkuVTnmMJ081xOeUUzQt37G5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c199c2ce42f1a67e794881f032c6725ddaaab5e0e2d368530d9408a8c0402642","last_reissued_at":"2026-07-05T11:12:52.444112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:52.444112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying Primary Stress Across Related Languages and Dialects with Transformer-based Speech Encoder Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ivan Porupski, Nikola Ljube\\v{s}i\\'c, Peter Rupnik","submitted_at":"2025-05-30T13:23:46Z","abstract_excerpt":"Automating primary stress identification has been an active research field due to the role of stress in encoding meaning and aiding speech comprehension. Previous studies relied mainly on traditional acoustic features and English datasets. In this paper, we investigate the approach of fine-tuning a pre-trained transformer model with an audio frame classification head. Our experiments use a new Croatian training dataset, with test sets in Croatian, Serbian, the Chakavian dialect, and Slovenian. By comparing an SVM classifier using traditional acoustic features with the fine-tuned speech transfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24571","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/2505.24571/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":"2505.24571","created_at":"2026-07-05T11:12:52.444175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24571v1","created_at":"2026-07-05T11:12:52.444175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24571","created_at":"2026-07-05T11:12:52.444175+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGM4FTSC6GTH","created_at":"2026-07-05T11:12:52.444175+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGM4FTSC6GTH46KI","created_at":"2026-07-05T11:12:52.444175+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGM4FTSC","created_at":"2026-07-05T11:12:52.444175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24571","citing_title":"Identifying Primary Stress Across Related Languages and Dialects with Transformer-based Speech Encoder Models","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX","json":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX.json","graph_json":"https://pith.science/api/pith-number/YGM4FTSC6GTH46KIQHYDFRTSLX/graph.json","events_json":"https://pith.science/api/pith-number/YGM4FTSC6GTH46KIQHYDFRTSLX/events.json","paper":"https://pith.science/paper/YGM4FTSC"},"agent_actions":{"view_html":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX","download_json":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX.json","view_paper":"https://pith.science/paper/YGM4FTSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24571&json=true","fetch_graph":"https://pith.science/api/pith-number/YGM4FTSC6GTH46KIQHYDFRTSLX/graph.json","fetch_events":"https://pith.science/api/pith-number/YGM4FTSC6GTH46KIQHYDFRTSLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX/action/storage_attestation","attest_author":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX/action/author_attestation","sign_citation":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX/action/citation_signature","submit_replication":"https://pith.science/pith/YGM4FTSC6GTH46KIQHYDFRTSLX/action/replication_record"}},"created_at":"2026-07-05T11:12:52.444175+00:00","updated_at":"2026-07-05T11:12:52.444175+00:00"}