{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Q2UQAOSA7BDCKVR6U4WMUHM6T6","short_pith_number":"pith:Q2UQAOSA","schema_version":"1.0","canonical_sha256":"86a9003a40f84625563ea72cca1d9e9f92501adbb58130921861dfd191c1e469","source":{"kind":"arxiv","id":"2104.06835","version":4},"attestation_state":"computed","paper":{"title":"Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changhe Song, Dan Su, Helen Meng, Jingbei Li, Yanyao Bian, Yixuan Zhou, Zhiyong Wu","submitted_at":"2021-04-14T13:09:51Z","abstract_excerpt":"Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to embody semantic information and employed to TTS recently. However, original or simply fine-tuned BERT embeddings still cannot provide sufficient semantic knowledge that expressive TTS models should take into account. In this paper, we propose a word-level semantic representation enhancing method based on dependency structure and pre-trained BERT embedding. The"},"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":"2104.06835","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T13:09:51Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4bd9d80d801bd7b0b467add624c93727be608f7147ff8fe2049498f604765103","abstract_canon_sha256":"3caba4379a303a5cedddb362e49e2e42a8059fee2e174bd66748631c91e91a83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:08.492238Z","signature_b64":"rUwV3xopxMRx9isHDZxLl3+Jc8SvL0t6Npx3txj2lI0zWOLZOkke79EtpPAOgbMTwqTWzNZN3kB1MC8SFGVuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86a9003a40f84625563ea72cca1d9e9f92501adbb58130921861dfd191c1e469","last_reissued_at":"2026-07-05T05:15:08.491820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:08.491820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changhe Song, Dan Su, Helen Meng, Jingbei Li, Yanyao Bian, Yixuan Zhou, Zhiyong Wu","submitted_at":"2021-04-14T13:09:51Z","abstract_excerpt":"Exploiting rich linguistic information in raw text is crucial for expressive text-to-speech (TTS). As large scale pre-trained text representation develops, bidirectional encoder representations from Transformers (BERT) has been proven to embody semantic information and employed to TTS recently. However, original or simply fine-tuned BERT embeddings still cannot provide sufficient semantic knowledge that expressive TTS models should take into account. In this paper, we propose a word-level semantic representation enhancing method based on dependency structure and pre-trained BERT embedding. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06835","kind":"arxiv","version":4},"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/2104.06835/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":"2104.06835","created_at":"2026-07-05T05:15:08.491876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06835v4","created_at":"2026-07-05T05:15:08.491876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06835","created_at":"2026-07-05T05:15:08.491876+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2UQAOSA7BDC","created_at":"2026-07-05T05:15:08.491876+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2UQAOSA7BDCKVR6","created_at":"2026-07-05T05:15:08.491876+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2UQAOSA","created_at":"2026-07-05T05:15:08.491876+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/Q2UQAOSA7BDCKVR6U4WMUHM6T6","json":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6.json","graph_json":"https://pith.science/api/pith-number/Q2UQAOSA7BDCKVR6U4WMUHM6T6/graph.json","events_json":"https://pith.science/api/pith-number/Q2UQAOSA7BDCKVR6U4WMUHM6T6/events.json","paper":"https://pith.science/paper/Q2UQAOSA"},"agent_actions":{"view_html":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6","download_json":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6.json","view_paper":"https://pith.science/paper/Q2UQAOSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06835&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2UQAOSA7BDCKVR6U4WMUHM6T6/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2UQAOSA7BDCKVR6U4WMUHM6T6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6/action/storage_attestation","attest_author":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6/action/author_attestation","sign_citation":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6/action/citation_signature","submit_replication":"https://pith.science/pith/Q2UQAOSA7BDCKVR6U4WMUHM6T6/action/replication_record"}},"created_at":"2026-07-05T05:15:08.491876+00:00","updated_at":"2026-07-05T05:15:08.491876+00:00"}