{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:74RJZSBVJQ6NLCZ2GU4ODNVJQX","short_pith_number":"pith:74RJZSBV","schema_version":"1.0","canonical_sha256":"ff229cc8354c3cd58b3a3538e1b6a985e4c49675823b8942fbbfbef801cf8b61","source":{"kind":"arxiv","id":"1702.06378","version":4},"attestation_state":"computed","paper":{"title":"Multitask Learning with CTC and Segmental CRF for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Liang Lu, Lingpeng Kong, Noah A. Smith","submitted_at":"2017-02-21T13:39:35Z","abstract_excerpt":"Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by marginalizing decisions about latent segmentation alternatives to derive a sequence probability: the former uses a globally normalized joint model of segment labels and durations, and the latter classifies each frame as either an output symbol or a \"continuation\" of the previous label. In this paper, we train a recognition model by optimizing an interpolation bet"},"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":"1702.06378","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-21T13:39:35Z","cross_cats_sorted":[],"title_canon_sha256":"84df72dad6dc9e802628f5f845c95c1ec7cedc8fea2f3d3d4e7a431667b0bddf","abstract_canon_sha256":"b7dfa3bca0c4761c5b650a436aa2faf3f3f585ac87a7f411a700bf12dc413eae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:58.334457Z","signature_b64":"uZV9Zy5HkLjq5YzOwJhGBMt9Lk+1YjGBVchqAqCq5cNi8tece2cNyeFfEYfFHk3OG3OGaP4/zh+dhQx59uQyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff229cc8354c3cd58b3a3538e1b6a985e4c49675823b8942fbbfbef801cf8b61","last_reissued_at":"2026-05-18T00:42:58.333729Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:58.333729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multitask Learning with CTC and Segmental CRF for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Liang Lu, Lingpeng Kong, Noah A. Smith","submitted_at":"2017-02-21T13:39:35Z","abstract_excerpt":"Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by marginalizing decisions about latent segmentation alternatives to derive a sequence probability: the former uses a globally normalized joint model of segment labels and durations, and the latter classifies each frame as either an output symbol or a \"continuation\" of the previous label. In this paper, we train a recognition model by optimizing an interpolation bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06378","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1702.06378","created_at":"2026-05-18T00:42:58.333845+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.06378v4","created_at":"2026-05-18T00:42:58.333845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06378","created_at":"2026-05-18T00:42:58.333845+00:00"},{"alias_kind":"pith_short_12","alias_value":"74RJZSBVJQ6N","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"74RJZSBVJQ6NLCZ2","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"74RJZSBV","created_at":"2026-05-18T12:31:03.183658+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/74RJZSBVJQ6NLCZ2GU4ODNVJQX","json":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX.json","graph_json":"https://pith.science/api/pith-number/74RJZSBVJQ6NLCZ2GU4ODNVJQX/graph.json","events_json":"https://pith.science/api/pith-number/74RJZSBVJQ6NLCZ2GU4ODNVJQX/events.json","paper":"https://pith.science/paper/74RJZSBV"},"agent_actions":{"view_html":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX","download_json":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX.json","view_paper":"https://pith.science/paper/74RJZSBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.06378&json=true","fetch_graph":"https://pith.science/api/pith-number/74RJZSBVJQ6NLCZ2GU4ODNVJQX/graph.json","fetch_events":"https://pith.science/api/pith-number/74RJZSBVJQ6NLCZ2GU4ODNVJQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX/action/storage_attestation","attest_author":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX/action/author_attestation","sign_citation":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX/action/citation_signature","submit_replication":"https://pith.science/pith/74RJZSBVJQ6NLCZ2GU4ODNVJQX/action/replication_record"}},"created_at":"2026-05-18T00:42:58.333845+00:00","updated_at":"2026-05-18T00:42:58.333845+00:00"}