{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LHIRXRQQF5VULBKL6NGLAL6FGH","short_pith_number":"pith:LHIRXRQQ","schema_version":"1.0","canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","source":{"kind":"arxiv","id":"2010.10203","version":2},"attestation_state":"computed","paper":{"title":"Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Balint Miklos, Bogdan Prisacari, Daniel Valcarce, Daria Soboleva, Felix Weissenberger, Julia Proskurnia, Justin Lu, M\\'arius \\v{S}ajgal\\'ik, Ondrej Skopek, Rohit Prabhavalkar, Victor C\\u{a}rbune","submitted_at":"2020-10-20T11:30:26Z","abstract_excerpt":"We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a prosody-aware text-to-speech system, we can outperform a model trained with expensive human audio recordings on the unspoken punctuation prediction problem. Our model architecture is well suited for on-device use. This is achieved by leveraging hash-based embeddings of automatic speech recognition text output in conjunction with acoustic features as input to a "},"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":"2010.10203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-20T11:30:26Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"9ca6b35432d07ad8c16cb30c6e3cfe576f6d89ca8b00395d2cc7c63ad2c97a15","abstract_canon_sha256":"85c1450bc43f1d5940e65f6847b4cbf159187243393c00789f6ee11b3b99fa7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:31.736453Z","signature_b64":"yYtOF/342Wz39xuErqm3YI4CMM4k+NVA3KRoHB0sNS9UAzT9fOvonvOQLjwV4jxrjZIC+9+sgVntfjHg4Tq+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d11bc6102f6b45854bf34cb02fc531e56847dbb2bc0e7c831932abe1c23793","last_reissued_at":"2026-07-05T02:14:31.735965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:31.735965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Balint Miklos, Bogdan Prisacari, Daniel Valcarce, Daria Soboleva, Felix Weissenberger, Julia Proskurnia, Justin Lu, M\\'arius \\v{S}ajgal\\'ik, Ondrej Skopek, Rohit Prabhavalkar, Victor C\\u{a}rbune","submitted_at":"2020-10-20T11:30:26Z","abstract_excerpt":"We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a prosody-aware text-to-speech system, we can outperform a model trained with expensive human audio recordings on the unspoken punctuation prediction problem. Our model architecture is well suited for on-device use. This is achieved by leveraging hash-based embeddings of automatic speech recognition text output in conjunction with acoustic features as input to a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10203","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/2010.10203/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":"2010.10203","created_at":"2026-07-05T02:14:31.736025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.10203v2","created_at":"2026-07-05T02:14:31.736025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10203","created_at":"2026-07-05T02:14:31.736025+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHIRXRQQF5VU","created_at":"2026-07-05T02:14:31.736025+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHIRXRQQF5VULBKL","created_at":"2026-07-05T02:14:31.736025+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHIRXRQQ","created_at":"2026-07-05T02:14:31.736025+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/LHIRXRQQF5VULBKL6NGLAL6FGH","json":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH.json","graph_json":"https://pith.science/api/pith-number/LHIRXRQQF5VULBKL6NGLAL6FGH/graph.json","events_json":"https://pith.science/api/pith-number/LHIRXRQQF5VULBKL6NGLAL6FGH/events.json","paper":"https://pith.science/paper/LHIRXRQQ"},"agent_actions":{"view_html":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH","download_json":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH.json","view_paper":"https://pith.science/paper/LHIRXRQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.10203&json=true","fetch_graph":"https://pith.science/api/pith-number/LHIRXRQQF5VULBKL6NGLAL6FGH/graph.json","fetch_events":"https://pith.science/api/pith-number/LHIRXRQQF5VULBKL6NGLAL6FGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/action/storage_attestation","attest_author":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/action/author_attestation","sign_citation":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/action/citation_signature","submit_replication":"https://pith.science/pith/LHIRXRQQF5VULBKL6NGLAL6FGH/action/replication_record"}},"created_at":"2026-07-05T02:14:31.736025+00:00","updated_at":"2026-07-05T02:14:31.736025+00:00"}