{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DPMSSXY7C2WC5JNJPTN2VBXJNC","short_pith_number":"pith:DPMSSXY7","schema_version":"1.0","canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","source":{"kind":"arxiv","id":"1807.00543","version":1},"attestation_state":"computed","paper":{"title":"Punctuation Prediction Model for Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian Szymczak, Jan Mizgajski, Najim Dehak, Piotr Szyma\\'nski, Piotr \\.Zelasko, Yishay Carmiel","submitted_at":"2018-07-02T09:06:27Z","abstract_excerpt":"An ASR system usually does not predict any punctuation or capitalization. Lack of punctuation causes problems in result presentation and confuses both the human reader andoff-the-shelf natural language processing algorithms. To overcome these limitations, we train two variants of Deep Neural Network (DNN) sequence labelling models - a Bidirectional Long Short-Term Memory (BLSTM) and a Convolutional Neural Network (CNN), to predict the punctuation. The models are trained on the Fisher corpus which includes punctuation annotation. In our experiments, we combine time-aligned and punctuated Fisher"},"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":"1807.00543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-02T09:06:27Z","cross_cats_sorted":[],"title_canon_sha256":"3ab41dca2a4aa9d02a5208be430997ab79671e5fa796853d213334477aa99674","abstract_canon_sha256":"71ad59d4489c1177c106421cfd2144a3fa291f8aa1cda37116605c5e42e8c56c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:52.237701Z","signature_b64":"1jHTQnuZ/FspwFSBFf+vD7f8eYi1g5P7IRtSmEmWCNSFqYphWhJfkFIHGlnkvRnmim9JLZ0HN+IKxA3U/RomCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd9295f1f16ac2ea5a97cdbaa86e968a3d086f7953aa9851efc00745b5f5c36","last_reissued_at":"2026-05-18T00:11:52.236961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:52.236961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Punctuation Prediction Model for Conversational Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adrian Szymczak, Jan Mizgajski, Najim Dehak, Piotr Szyma\\'nski, Piotr \\.Zelasko, Yishay Carmiel","submitted_at":"2018-07-02T09:06:27Z","abstract_excerpt":"An ASR system usually does not predict any punctuation or capitalization. Lack of punctuation causes problems in result presentation and confuses both the human reader andoff-the-shelf natural language processing algorithms. To overcome these limitations, we train two variants of Deep Neural Network (DNN) sequence labelling models - a Bidirectional Long Short-Term Memory (BLSTM) and a Convolutional Neural Network (CNN), to predict the punctuation. The models are trained on the Fisher corpus which includes punctuation annotation. In our experiments, we combine time-aligned and punctuated Fisher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00543","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":""},"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":"1807.00543","created_at":"2026-05-18T00:11:52.237071+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00543v1","created_at":"2026-05-18T00:11:52.237071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00543","created_at":"2026-05-18T00:11:52.237071+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPMSSXY7C2WC","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPMSSXY7C2WC5JNJ","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPMSSXY7","created_at":"2026-05-18T12:32:19.392346+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/DPMSSXY7C2WC5JNJPTN2VBXJNC","json":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC.json","graph_json":"https://pith.science/api/pith-number/DPMSSXY7C2WC5JNJPTN2VBXJNC/graph.json","events_json":"https://pith.science/api/pith-number/DPMSSXY7C2WC5JNJPTN2VBXJNC/events.json","paper":"https://pith.science/paper/DPMSSXY7"},"agent_actions":{"view_html":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC","download_json":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC.json","view_paper":"https://pith.science/paper/DPMSSXY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00543&json=true","fetch_graph":"https://pith.science/api/pith-number/DPMSSXY7C2WC5JNJPTN2VBXJNC/graph.json","fetch_events":"https://pith.science/api/pith-number/DPMSSXY7C2WC5JNJPTN2VBXJNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/action/storage_attestation","attest_author":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/action/author_attestation","sign_citation":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/action/citation_signature","submit_replication":"https://pith.science/pith/DPMSSXY7C2WC5JNJPTN2VBXJNC/action/replication_record"}},"created_at":"2026-05-18T00:11:52.237071+00:00","updated_at":"2026-05-18T00:11:52.237071+00:00"}