{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZHRGZWRRBMFPIPPK5RMQHQ53VE","short_pith_number":"pith:ZHRGZWRR","schema_version":"1.0","canonical_sha256":"c9e26cda310b0af43deaec5903c3bba92bc76fdb1e4262fe59fd81f881b6cf0a","source":{"kind":"arxiv","id":"2203.00232","version":1},"attestation_state":"computed","paper":{"title":"Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jonathan Le Roux, Niko Moritz, Shinji Watanabe, Takaaki Hori, Xuankai Chang","submitted_at":"2022-03-01T05:02:02Z","abstract_excerpt":"Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. For example, GTC was first used to encode an N-best list of pseudo-label sequences into a graph for semi-supervised learning. In this paper, we propose an extension of GTC to model the posteriors of both labels and label transitions by a neural network, which can be applied to a wider range of tasks. As an example application, we use the extended GTC (GTC-e) for the multi-speak"},"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":"2203.00232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-01T05:02:02Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"ada1b3e770ab184638d4447849de8813868ff046dc5fa8014863e0fb07041335","abstract_canon_sha256":"f35c86b954c3b47adbcc0ff4358cdd5724554b64e7adf7a380b145c37a6ce00a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:15.360461Z","signature_b64":"I5iRXZnM9FPZ5fMru97avQOwq7/69V5Q1DwXIvpSrUC337RugYGhLOrznc5HAyoynjiE+ftGfB56FUGqnOXeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9e26cda310b0af43deaec5903c3bba92bc76fdb1e4262fe59fd81f881b6cf0a","last_reissued_at":"2026-07-05T04:01:15.359954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:15.359954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jonathan Le Roux, Niko Moritz, Shinji Watanabe, Takaaki Hori, Xuankai Chang","submitted_at":"2022-03-01T05:02:02Z","abstract_excerpt":"Graph-based temporal classification (GTC), a generalized form of the connectionist temporal classification loss, was recently proposed to improve automatic speech recognition (ASR) systems using graph-based supervision. For example, GTC was first used to encode an N-best list of pseudo-label sequences into a graph for semi-supervised learning. In this paper, we propose an extension of GTC to model the posteriors of both labels and label transitions by a neural network, which can be applied to a wider range of tasks. As an example application, we use the extended GTC (GTC-e) for the multi-speak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00232","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/2203.00232/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":"2203.00232","created_at":"2026-07-05T04:01:15.360014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00232v1","created_at":"2026-07-05T04:01:15.360014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00232","created_at":"2026-07-05T04:01:15.360014+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHRGZWRRBMFP","created_at":"2026-07-05T04:01:15.360014+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHRGZWRRBMFPIPPK","created_at":"2026-07-05T04:01:15.360014+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHRGZWRR","created_at":"2026-07-05T04:01:15.360014+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/ZHRGZWRRBMFPIPPK5RMQHQ53VE","json":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE.json","graph_json":"https://pith.science/api/pith-number/ZHRGZWRRBMFPIPPK5RMQHQ53VE/graph.json","events_json":"https://pith.science/api/pith-number/ZHRGZWRRBMFPIPPK5RMQHQ53VE/events.json","paper":"https://pith.science/paper/ZHRGZWRR"},"agent_actions":{"view_html":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE","download_json":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE.json","view_paper":"https://pith.science/paper/ZHRGZWRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00232&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHRGZWRRBMFPIPPK5RMQHQ53VE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHRGZWRRBMFPIPPK5RMQHQ53VE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE/action/storage_attestation","attest_author":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE/action/author_attestation","sign_citation":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE/action/citation_signature","submit_replication":"https://pith.science/pith/ZHRGZWRRBMFPIPPK5RMQHQ53VE/action/replication_record"}},"created_at":"2026-07-05T04:01:15.360014+00:00","updated_at":"2026-07-05T04:01:15.360014+00:00"}