{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:55TY6UNY4LYFYRJAHN2RSPMDPO","short_pith_number":"pith:55TY6UNY","schema_version":"1.0","canonical_sha256":"ef678f51b8e2f05c45203b75193d837b82a70f549707592fcfa7d26d0da8e382","source":{"kind":"arxiv","id":"2104.02014","version":2},"attestation_state":"computed","paper":{"title":"SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Georg Kucsko, Jagadeesh Balam, Keenan Freyberg, Michael D. Shulman, Oleksii Kuchaiev, Patrick K. O'Neill, Shinji Watanabe, Somshubra Majumdar, Vahid Noroozi, Vitaly Lavrukhin, Yuekai Zhang, Yuliya Dovzhenko","submitted_at":"2021-04-05T17:05:28Z","abstract_excerpt":"In the English speech-to-text (STT) machine learning task, acoustic models are conventionally trained on uncased Latin characters, and any necessary orthography (such as capitalization, punctuation, and denormalization of non-standard words) is imputed by separate post-processing models. This adds complexity and limits performance, as many formatting tasks benefit from semantic information present in the acoustic signal but absent in transcription. Here we propose a new STT task: end-to-end neural transcription with fully formatted text for target labels. We present baseline Conformer-based mo"},"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":"2104.02014","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-05T17:05:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"fe2e1d8f516d5e9e5bcf0f15184832c53f0892cf1c6e337935af6e6a6ea0b618","abstract_canon_sha256":"cbf0b842d71322da39128d4a496311aa8be086a3ddfaad41b064b72696aee7b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:13.417984Z","signature_b64":"CIttiZ/5cNuGjl6/rojs3qo6hpo5Txb1BlzxrzhXnKTO2d54QAsTzAN58lHCHkrUrcTDYQbAGywl9DID4wAxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef678f51b8e2f05c45203b75193d837b82a70f549707592fcfa7d26d0da8e382","last_reissued_at":"2026-07-05T02:29:13.417468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:13.417468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Georg Kucsko, Jagadeesh Balam, Keenan Freyberg, Michael D. Shulman, Oleksii Kuchaiev, Patrick K. O'Neill, Shinji Watanabe, Somshubra Majumdar, Vahid Noroozi, Vitaly Lavrukhin, Yuekai Zhang, Yuliya Dovzhenko","submitted_at":"2021-04-05T17:05:28Z","abstract_excerpt":"In the English speech-to-text (STT) machine learning task, acoustic models are conventionally trained on uncased Latin characters, and any necessary orthography (such as capitalization, punctuation, and denormalization of non-standard words) is imputed by separate post-processing models. This adds complexity and limits performance, as many formatting tasks benefit from semantic information present in the acoustic signal but absent in transcription. Here we propose a new STT task: end-to-end neural transcription with fully formatted text for target labels. We present baseline Conformer-based mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02014","kind":"arxiv","version":2},"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/2104.02014/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":"2104.02014","created_at":"2026-07-05T02:29:13.417536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02014v2","created_at":"2026-07-05T02:29:13.417536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02014","created_at":"2026-07-05T02:29:13.417536+00:00"},{"alias_kind":"pith_short_12","alias_value":"55TY6UNY4LYF","created_at":"2026-07-05T02:29:13.417536+00:00"},{"alias_kind":"pith_short_16","alias_value":"55TY6UNY4LYFYRJA","created_at":"2026-07-05T02:29:13.417536+00:00"},{"alias_kind":"pith_short_8","alias_value":"55TY6UNY","created_at":"2026-07-05T02:29:13.417536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08486","citing_title":"TRADE: Transducer-Augmented Decoder for Speech LLM","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20830","citing_title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08003","citing_title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16767","citing_title":"When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO","json":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO.json","graph_json":"https://pith.science/api/pith-number/55TY6UNY4LYFYRJAHN2RSPMDPO/graph.json","events_json":"https://pith.science/api/pith-number/55TY6UNY4LYFYRJAHN2RSPMDPO/events.json","paper":"https://pith.science/paper/55TY6UNY"},"agent_actions":{"view_html":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO","download_json":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO.json","view_paper":"https://pith.science/paper/55TY6UNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02014&json=true","fetch_graph":"https://pith.science/api/pith-number/55TY6UNY4LYFYRJAHN2RSPMDPO/graph.json","fetch_events":"https://pith.science/api/pith-number/55TY6UNY4LYFYRJAHN2RSPMDPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO/action/storage_attestation","attest_author":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO/action/author_attestation","sign_citation":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO/action/citation_signature","submit_replication":"https://pith.science/pith/55TY6UNY4LYFYRJAHN2RSPMDPO/action/replication_record"}},"created_at":"2026-07-05T02:29:13.417536+00:00","updated_at":"2026-07-05T02:29:13.417536+00:00"}