{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QLGROEPETBUG5JAXOVDKEZWTTO","short_pith_number":"pith:QLGROEPE","schema_version":"1.0","canonical_sha256":"82cd1711e498686ea4177546a266d39bbc8d949004eb366851c9ec5ecc7e8cf0","source":{"kind":"arxiv","id":"2107.12428","version":1},"attestation_state":"computed","paper":{"title":"Improving Word Recognition in Speech Transcriptions by Decision-level Fusion of Stemming and Two-way Phoneme Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Seba Susan, Sunakshi Mehra","submitted_at":"2021-07-26T18:44:24Z","abstract_excerpt":"We introduce an unsupervised approach for correcting highly imperfect speech transcriptions based on a decision-level fusion of stemming and two-way phoneme pruning. Transcripts are acquired from videos by extracting audio using Ffmpeg framework and further converting audio to text transcript using Google API. In the benchmark LRW dataset, there are 500 word categories, and 50 videos per class in mp4 format. All videos consist of 29 frames (each 1.16 s long) and the word appears in the middle of the video. In our approach we tried to improve the baseline accuracy from 9.34% by using stemming, "},"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":"2107.12428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-26T18:44:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f69f07647d16149e3d73266dca9d5d921f335767146ed5e5db6c8b005500f741","abstract_canon_sha256":"b9778274a72d86c6c83b7c338c853ed71b1be3a7429ac7d8b1bc8d3e57bfa4e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:56.214995Z","signature_b64":"VX2o6YcB7O+2P87DmwghPghnlew/S8dFuo3KzOpL9vzijxMxM1QTGwe9WPRBGcqdFJLJHyuOLQBuzmXh7RorAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82cd1711e498686ea4177546a266d39bbc8d949004eb366851c9ec5ecc7e8cf0","last_reissued_at":"2026-07-05T03:00:56.214661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:56.214661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Word Recognition in Speech Transcriptions by Decision-level Fusion of Stemming and Two-way Phoneme Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Seba Susan, Sunakshi Mehra","submitted_at":"2021-07-26T18:44:24Z","abstract_excerpt":"We introduce an unsupervised approach for correcting highly imperfect speech transcriptions based on a decision-level fusion of stemming and two-way phoneme pruning. Transcripts are acquired from videos by extracting audio using Ffmpeg framework and further converting audio to text transcript using Google API. In the benchmark LRW dataset, there are 500 word categories, and 50 videos per class in mp4 format. All videos consist of 29 frames (each 1.16 s long) and the word appears in the middle of the video. In our approach we tried to improve the baseline accuracy from 9.34% by using stemming, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.12428","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/2107.12428/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":"2107.12428","created_at":"2026-07-05T03:00:56.214710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.12428v1","created_at":"2026-07-05T03:00:56.214710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.12428","created_at":"2026-07-05T03:00:56.214710+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLGROEPETBUG","created_at":"2026-07-05T03:00:56.214710+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLGROEPETBUG5JAX","created_at":"2026-07-05T03:00:56.214710+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLGROEPE","created_at":"2026-07-05T03:00:56.214710+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/QLGROEPETBUG5JAXOVDKEZWTTO","json":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO.json","graph_json":"https://pith.science/api/pith-number/QLGROEPETBUG5JAXOVDKEZWTTO/graph.json","events_json":"https://pith.science/api/pith-number/QLGROEPETBUG5JAXOVDKEZWTTO/events.json","paper":"https://pith.science/paper/QLGROEPE"},"agent_actions":{"view_html":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO","download_json":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO.json","view_paper":"https://pith.science/paper/QLGROEPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.12428&json=true","fetch_graph":"https://pith.science/api/pith-number/QLGROEPETBUG5JAXOVDKEZWTTO/graph.json","fetch_events":"https://pith.science/api/pith-number/QLGROEPETBUG5JAXOVDKEZWTTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO/action/storage_attestation","attest_author":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO/action/author_attestation","sign_citation":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO/action/citation_signature","submit_replication":"https://pith.science/pith/QLGROEPETBUG5JAXOVDKEZWTTO/action/replication_record"}},"created_at":"2026-07-05T03:00:56.214710+00:00","updated_at":"2026-07-05T03:00:56.214710+00:00"}