{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U5FH3M5USAWH73YNF3LBX4CU7R","short_pith_number":"pith:U5FH3M5U","schema_version":"1.0","canonical_sha256":"a74a7db3b4902c7fef0d2ed61bf054fc44f397e380d42bf7a06bd12693e388cc","source":{"kind":"arxiv","id":"2606.27717","version":1},"attestation_state":"computed","paper":{"title":"Do Speech Emphasis Models Generalize across Languages and Emotions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Deepali Aneja, Haonan Chen, Jiaqi Su, Megan Wei, Yunyun Wang, Zeyu Jin","submitted_at":"2026-06-26T04:54:43Z","abstract_excerpt":"Prosodic emphasis varies across languages, emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read speech. We introduce MMEE (Multilingual Multi-Emotion Emphasis), a corpus of 10,000 professionally recorded expressive utterances (14.13 hours) across 7 languages and 34 emotion/style categories, with three-level perceptual labels (10 annotations per sample). We benchmark two state-of-the-art architectures under monolingual, cross-lingual, multilingual, cross-emotion, cross-dataset, and data-scale settings. Monolingual mo"},"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":"2606.27717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T04:54:43Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"1f54a2c208dac87d7f88c296539272c54eee530c8d05526af38eb78df5b4d53f","abstract_canon_sha256":"2a77d5b70a803c2aaf11432ce0ac33c799a76850802c1acdc0cbdfc2a2b13ee7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:46.297946Z","signature_b64":"NumfFvzelrhMZJg53pMOJPuc1uwLqAr1pW7/wCg0EY0jA39/UzjuaCeb/jiE4hgTW9LTGtBIxCzROeb3W7cXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a74a7db3b4902c7fef0d2ed61bf054fc44f397e380d42bf7a06bd12693e388cc","last_reissued_at":"2026-06-29T01:14:46.297464Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:46.297464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Speech Emphasis Models Generalize across Languages and Emotions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Deepali Aneja, Haonan Chen, Jiaqi Su, Megan Wei, Yunyun Wang, Zeyu Jin","submitted_at":"2026-06-26T04:54:43Z","abstract_excerpt":"Prosodic emphasis varies across languages, emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read speech. We introduce MMEE (Multilingual Multi-Emotion Emphasis), a corpus of 10,000 professionally recorded expressive utterances (14.13 hours) across 7 languages and 34 emotion/style categories, with three-level perceptual labels (10 annotations per sample). We benchmark two state-of-the-art architectures under monolingual, cross-lingual, multilingual, cross-emotion, cross-dataset, and data-scale settings. Monolingual mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27717","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/2606.27717/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":"2606.27717","created_at":"2026-06-29T01:14:46.297522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27717v1","created_at":"2026-06-29T01:14:46.297522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27717","created_at":"2026-06-29T01:14:46.297522+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5FH3M5USAWH","created_at":"2026-06-29T01:14:46.297522+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5FH3M5USAWH73YN","created_at":"2026-06-29T01:14:46.297522+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5FH3M5U","created_at":"2026-06-29T01:14:46.297522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27717","citing_title":"Do Speech Emphasis Models Generalize across Languages and Emotions?","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R","json":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R.json","graph_json":"https://pith.science/api/pith-number/U5FH3M5USAWH73YNF3LBX4CU7R/graph.json","events_json":"https://pith.science/api/pith-number/U5FH3M5USAWH73YNF3LBX4CU7R/events.json","paper":"https://pith.science/paper/U5FH3M5U"},"agent_actions":{"view_html":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R","download_json":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R.json","view_paper":"https://pith.science/paper/U5FH3M5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27717&json=true","fetch_graph":"https://pith.science/api/pith-number/U5FH3M5USAWH73YNF3LBX4CU7R/graph.json","fetch_events":"https://pith.science/api/pith-number/U5FH3M5USAWH73YNF3LBX4CU7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R/action/storage_attestation","attest_author":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R/action/author_attestation","sign_citation":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R/action/citation_signature","submit_replication":"https://pith.science/pith/U5FH3M5USAWH73YNF3LBX4CU7R/action/replication_record"}},"created_at":"2026-06-29T01:14:46.297522+00:00","updated_at":"2026-06-29T01:14:46.297522+00:00"}