{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NZ6Z5GPJWARPO3ULOPIB7MLIL2","short_pith_number":"pith:NZ6Z5GPJ","schema_version":"1.0","canonical_sha256":"6e7d9e99e9b022f76e8b73d01fb1685ead7f1c79522806255c00210bb10a7923","source":{"kind":"arxiv","id":"2306.11473","version":1},"attestation_state":"computed","paper":{"title":"Timestamped Embedding-Matching Acoustic-to-Word CTC ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Woojay Jeon","submitted_at":"2023-06-20T11:53:43Z","abstract_excerpt":"In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by many real-world applications, in addition to the transcription. The word timestamps enable the ASR to output word segmentations and word confusion networks without relying on a secondary model or forced alignment process when testing. Our proposed system has similar word segmentation accuracy as a hybrid DNN-HMM (Deep Neural Network-Hidden Markov Model) syste"},"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":"2306.11473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T11:53:43Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cfc5eaf04f341bc4d08e4774e0603743d69215bd86a192cc308ac8d4bc21fbe0","abstract_canon_sha256":"d1fd57ee021fd0b7aefb794f0f558043c128d64cc076dc321b642fed8976a0db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:20.171075Z","signature_b64":"IWTf2fimNG8vEEZ29HET1AqBPTgZAGDQGgu5AInG09hEX2MFd7FtBiqL5/FBSO4yNQB5GYagYM+vM33ohU+MBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e7d9e99e9b022f76e8b73d01fb1685ead7f1c79522806255c00210bb10a7923","last_reissued_at":"2026-07-05T06:22:20.170672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:20.170672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Timestamped Embedding-Matching Acoustic-to-Word CTC ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Woojay Jeon","submitted_at":"2023-06-20T11:53:43Z","abstract_excerpt":"In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by many real-world applications, in addition to the transcription. The word timestamps enable the ASR to output word segmentations and word confusion networks without relying on a secondary model or forced alignment process when testing. Our proposed system has similar word segmentation accuracy as a hybrid DNN-HMM (Deep Neural Network-Hidden Markov Model) syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11473","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/2306.11473/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":"2306.11473","created_at":"2026-07-05T06:22:20.170726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11473v1","created_at":"2026-07-05T06:22:20.170726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11473","created_at":"2026-07-05T06:22:20.170726+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZ6Z5GPJWARP","created_at":"2026-07-05T06:22:20.170726+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZ6Z5GPJWARPO3UL","created_at":"2026-07-05T06:22:20.170726+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZ6Z5GPJ","created_at":"2026-07-05T06:22:20.170726+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/NZ6Z5GPJWARPO3ULOPIB7MLIL2","json":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2.json","graph_json":"https://pith.science/api/pith-number/NZ6Z5GPJWARPO3ULOPIB7MLIL2/graph.json","events_json":"https://pith.science/api/pith-number/NZ6Z5GPJWARPO3ULOPIB7MLIL2/events.json","paper":"https://pith.science/paper/NZ6Z5GPJ"},"agent_actions":{"view_html":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2","download_json":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2.json","view_paper":"https://pith.science/paper/NZ6Z5GPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11473&json=true","fetch_graph":"https://pith.science/api/pith-number/NZ6Z5GPJWARPO3ULOPIB7MLIL2/graph.json","fetch_events":"https://pith.science/api/pith-number/NZ6Z5GPJWARPO3ULOPIB7MLIL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2/action/storage_attestation","attest_author":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2/action/author_attestation","sign_citation":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2/action/citation_signature","submit_replication":"https://pith.science/pith/NZ6Z5GPJWARPO3ULOPIB7MLIL2/action/replication_record"}},"created_at":"2026-07-05T06:22:20.170726+00:00","updated_at":"2026-07-05T06:22:20.170726+00:00"}