{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PLRKIF3W3K26R7EBQYVYMAEXJ3","short_pith_number":"pith:PLRKIF3W","schema_version":"1.0","canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","source":{"kind":"arxiv","id":"2306.01296","version":1},"attestation_state":"computed","paper":{"title":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Hanbyul Kim, Lukas Lee, Seolki Baek, Seunghyun Seo","submitted_at":"2023-06-02T06:46:14Z","abstract_excerpt":"Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is particularly desirable but presents a difficult technical challenge. In this work, we propose a method for predicting punctuated text from input speech using a chunk-based Transformer encoder trained with Connectionist Temporal Classification (CTC) loss. The acoustic model trained with long sequences by concatenating the input and target sequences can learn punctuati"},"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":"2306.01296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-02T06:46:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"87143942be3730241e4915ac3438c94580fb609ef3e026557e6df4446e419468","abstract_canon_sha256":"bc17d217f74052f5158c92f9aff90e2fd676a0d0147019837ffa54f530861712"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:29.122762Z","signature_b64":"jvYAO56NvfmXJ6rcvjRN9o0oKT4fEwEyHILQmEWirCNE1kTgtIQuC0ujIsAY0hvwc7k9yHQGIr0ySYO69yeUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae2a41776dab5e8fc81862b8600974ef6a858dfc3ec762aa96eccca2cd2e3d1","last_reissued_at":"2026-07-05T07:06:29.122310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:29.122310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Hanbyul Kim, Lukas Lee, Seolki Baek, Seunghyun Seo","submitted_at":"2023-06-02T06:46:14Z","abstract_excerpt":"Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is particularly desirable but presents a difficult technical challenge. In this work, we propose a method for predicting punctuated text from input speech using a chunk-based Transformer encoder trained with Connectionist Temporal Classification (CTC) loss. The acoustic model trained with long sequences by concatenating the input and target sequences can learn punctuati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01296","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/2306.01296/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":"2306.01296","created_at":"2026-07-05T07:06:29.122376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01296v1","created_at":"2026-07-05T07:06:29.122376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01296","created_at":"2026-07-05T07:06:29.122376+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLRKIF3W3K26","created_at":"2026-07-05T07:06:29.122376+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLRKIF3W3K26R7EB","created_at":"2026-07-05T07:06:29.122376+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLRKIF3W","created_at":"2026-07-05T07:06:29.122376+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/PLRKIF3W3K26R7EBQYVYMAEXJ3","json":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3.json","graph_json":"https://pith.science/api/pith-number/PLRKIF3W3K26R7EBQYVYMAEXJ3/graph.json","events_json":"https://pith.science/api/pith-number/PLRKIF3W3K26R7EBQYVYMAEXJ3/events.json","paper":"https://pith.science/paper/PLRKIF3W"},"agent_actions":{"view_html":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3","download_json":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3.json","view_paper":"https://pith.science/paper/PLRKIF3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01296&json=true","fetch_graph":"https://pith.science/api/pith-number/PLRKIF3W3K26R7EBQYVYMAEXJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/PLRKIF3W3K26R7EBQYVYMAEXJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/action/storage_attestation","attest_author":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/action/author_attestation","sign_citation":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/action/citation_signature","submit_replication":"https://pith.science/pith/PLRKIF3W3K26R7EBQYVYMAEXJ3/action/replication_record"}},"created_at":"2026-07-05T07:06:29.122376+00:00","updated_at":"2026-07-05T07:06:29.122376+00:00"}