{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2006:325PSL4D7KLO4QSQ3TFLHNUCUM","short_pith_number":"pith:325PSL4D","schema_version":"1.0","canonical_sha256":"debaf92f83fa96ee4250dccab3b682a32982ff2fa624bbf2ef5c5a65240b9dd6","source":{"kind":"arxiv","id":"cs/0612139","version":1},"attestation_state":"computed","paper":{"title":"Alignment of Speech to Highly Imperfect Text Transcriptions","license":"","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.SD","authors_text":"Alexander Haubold, John R. Kender","submitted_at":"2006-12-28T06:45:43Z","abstract_excerpt":"We introduce a novel and inexpensive approach for the temporal alignment of speech to highly imperfect transcripts from automatic speech recognition (ASR). Transcripts are generated for extended lecture and presentation videos, which in some cases feature more than 30 speakers with different accents, resulting in highly varying transcription qualities. In our approach we detect a subset of phonemes in the speech track, and align them to the sequence of phonemes extracted from the transcript. We report on the results for 4 speech-transcript sets ranging from 22 to 108 minutes. The alignment per"},"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":"cs/0612139","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.SD","submitted_at":"2006-12-28T06:45:43Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"007794a108470a7a555cfe6ccb73d774a5629cae20e5c1d46b1bc00d7e87cade","abstract_canon_sha256":"475ad73a5a191408ba800d34eb099ec754d59b728ceb3613d1cdba91001fbcb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:58:16.501445Z","signature_b64":"WzoyoaMoEDMUTuEsTLB4ko7OLKUAQnY3DonriqmsW2ZPgEnkViWbSXkcbZ+IBq+vvr4KRi/y0/OszyxKEwgaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"debaf92f83fa96ee4250dccab3b682a32982ff2fa624bbf2ef5c5a65240b9dd6","last_reissued_at":"2026-07-04T14:58:16.501020Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:58:16.501020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alignment of Speech to Highly Imperfect Text Transcriptions","license":"","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.SD","authors_text":"Alexander Haubold, John R. Kender","submitted_at":"2006-12-28T06:45:43Z","abstract_excerpt":"We introduce a novel and inexpensive approach for the temporal alignment of speech to highly imperfect transcripts from automatic speech recognition (ASR). Transcripts are generated for extended lecture and presentation videos, which in some cases feature more than 30 speakers with different accents, resulting in highly varying transcription qualities. In our approach we detect a subset of phonemes in the speech track, and align them to the sequence of phonemes extracted from the transcript. We report on the results for 4 speech-transcript sets ranging from 22 to 108 minutes. The alignment per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0612139","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/cs/0612139/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":"cs/0612139","created_at":"2026-07-04T14:58:16.501079+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0612139v1","created_at":"2026-07-04T14:58:16.501079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0612139","created_at":"2026-07-04T14:58:16.501079+00:00"},{"alias_kind":"pith_short_12","alias_value":"325PSL4D7KLO","created_at":"2026-07-04T14:58:16.501079+00:00"},{"alias_kind":"pith_short_16","alias_value":"325PSL4D7KLO4QSQ","created_at":"2026-07-04T14:58:16.501079+00:00"},{"alias_kind":"pith_short_8","alias_value":"325PSL4D","created_at":"2026-07-04T14:58:16.501079+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/325PSL4D7KLO4QSQ3TFLHNUCUM","json":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM.json","graph_json":"https://pith.science/api/pith-number/325PSL4D7KLO4QSQ3TFLHNUCUM/graph.json","events_json":"https://pith.science/api/pith-number/325PSL4D7KLO4QSQ3TFLHNUCUM/events.json","paper":"https://pith.science/paper/325PSL4D"},"agent_actions":{"view_html":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM","download_json":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM.json","view_paper":"https://pith.science/paper/325PSL4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0612139&json=true","fetch_graph":"https://pith.science/api/pith-number/325PSL4D7KLO4QSQ3TFLHNUCUM/graph.json","fetch_events":"https://pith.science/api/pith-number/325PSL4D7KLO4QSQ3TFLHNUCUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM/action/storage_attestation","attest_author":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM/action/author_attestation","sign_citation":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM/action/citation_signature","submit_replication":"https://pith.science/pith/325PSL4D7KLO4QSQ3TFLHNUCUM/action/replication_record"}},"created_at":"2026-07-04T14:58:16.501079+00:00","updated_at":"2026-07-04T14:58:16.501079+00:00"}