{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HONKOOGL7L2STW3GJWFP3DNVRO","short_pith_number":"pith:HONKOOGL","schema_version":"1.0","canonical_sha256":"3b9aa738cbfaf529db664d8afd8db58ba3a7012d869f334a8ea673c588dafc59","source":{"kind":"arxiv","id":"1708.00531","version":2},"attestation_state":"computed","paper":{"title":"End-to-End Neural Segmental Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Hao Tang, Karen Livescu, Kevin Gimpel, Liang Lu, Lingpeng Kong, Noah A. Smith, Steve Renals","submitted_at":"2017-08-01T21:53:56Z","abstract_excerpt":"Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time. Neural segmental models are segmental models that use neural network-based weight functions. Neural segmental models have achieved competitive results for speech recognition, and their end-to-end training has been explored in several studies. In this work, we review neural segmental models, which can be viewed as consisting of a neural network-based acoustic encoder and a finite-state transducer decoder. We s"},"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":"1708.00531","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T21:53:56Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"a7b3a7435f8394652fbb3db580e74794f95eb23d387a230e9a7f1394c9c8eeb2","abstract_canon_sha256":"ab005868c369f2c82aba35490009550833705af338db33977bca9f95ca5a8f86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:34.496438Z","signature_b64":"Sfy5WOwTzBXr31N3GoNclH/r6QVNsg+CagJoARKnE1vJXtRmjsofQMS7YfdI1A+ff5RS4AZv4iFx9/XYMZlXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b9aa738cbfaf529db664d8afd8db58ba3a7012d869f334a8ea673c588dafc59","last_reissued_at":"2026-05-18T00:23:34.495702Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:34.495702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Neural Segmental Models for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Chris Dyer, Hao Tang, Karen Livescu, Kevin Gimpel, Liang Lu, Lingpeng Kong, Noah A. Smith, Steve Renals","submitted_at":"2017-08-01T21:53:56Z","abstract_excerpt":"Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at a time. Neural segmental models are segmental models that use neural network-based weight functions. Neural segmental models have achieved competitive results for speech recognition, and their end-to-end training has been explored in several studies. In this work, we review neural segmental models, which can be viewed as consisting of a neural network-based acoustic encoder and a finite-state transducer decoder. We s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00531","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":""},"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":"1708.00531","created_at":"2026-05-18T00:23:34.495809+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.00531v2","created_at":"2026-05-18T00:23:34.495809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00531","created_at":"2026-05-18T00:23:34.495809+00:00"},{"alias_kind":"pith_short_12","alias_value":"HONKOOGL7L2S","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HONKOOGL7L2STW3G","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HONKOOGL","created_at":"2026-05-18T12:31:18.294218+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/HONKOOGL7L2STW3GJWFP3DNVRO","json":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO.json","graph_json":"https://pith.science/api/pith-number/HONKOOGL7L2STW3GJWFP3DNVRO/graph.json","events_json":"https://pith.science/api/pith-number/HONKOOGL7L2STW3GJWFP3DNVRO/events.json","paper":"https://pith.science/paper/HONKOOGL"},"agent_actions":{"view_html":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO","download_json":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO.json","view_paper":"https://pith.science/paper/HONKOOGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.00531&json=true","fetch_graph":"https://pith.science/api/pith-number/HONKOOGL7L2STW3GJWFP3DNVRO/graph.json","fetch_events":"https://pith.science/api/pith-number/HONKOOGL7L2STW3GJWFP3DNVRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO/action/storage_attestation","attest_author":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO/action/author_attestation","sign_citation":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO/action/citation_signature","submit_replication":"https://pith.science/pith/HONKOOGL7L2STW3GJWFP3DNVRO/action/replication_record"}},"created_at":"2026-05-18T00:23:34.495809+00:00","updated_at":"2026-05-18T00:23:34.495809+00:00"}