{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AVK4FVMXFEWLTQUJDRVSPM3FNJ","short_pith_number":"pith:AVK4FVMX","schema_version":"1.0","canonical_sha256":"0555c2d597292cb9c2891c6b27b3656a4f62c2a05a2eb0065d5120e18ba52460","source":{"kind":"arxiv","id":"2003.12687","version":2},"attestation_state":"computed","paper":{"title":"Serialized Output Training for End-to-End Overlapped Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Yashesh Gaur, Zhong Meng","submitted_at":"2020-03-28T02:37:09Z","abstract_excerpt":"This paper proposes serialized output training (SOT), a novel framework for multi-speaker overlapped speech recognition based on an attention-based encoder-decoder approach. Instead of having multiple output layers as with the permutation invariant training (PIT), SOT uses a model with only one output layer that generates the transcriptions of multiple speakers one after another. The attention and decoder modules take care of producing multiple transcriptions from overlapped speech. SOT has two advantages over PIT: (1) no limitation in the maximum number of speakers, and (2) an ability to mode"},"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":"2003.12687","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-28T02:37:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"849aff975b1649f4954e0d1bdab00dc7ba84190cd74552a26d7bfabc992058f6","abstract_canon_sha256":"ec963ef76fbd4b3adae2011ccd66338aeb30ada11880925baa2b29ebf28453e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:37.634713Z","signature_b64":"7ce5lYbFnogw+zHnYga/DqKCfXUsSvSQIKk4PAVBZItuD8gKMgiR5WwSG1pWOAKHm6QWD3Zz6/Dcm4pzjN7QCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0555c2d597292cb9c2891c6b27b3656a4f62c2a05a2eb0065d5120e18ba52460","last_reissued_at":"2026-07-05T01:25:37.634195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:37.634195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Serialized Output Training for End-to-End Overlapped Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Yashesh Gaur, Zhong Meng","submitted_at":"2020-03-28T02:37:09Z","abstract_excerpt":"This paper proposes serialized output training (SOT), a novel framework for multi-speaker overlapped speech recognition based on an attention-based encoder-decoder approach. Instead of having multiple output layers as with the permutation invariant training (PIT), SOT uses a model with only one output layer that generates the transcriptions of multiple speakers one after another. The attention and decoder modules take care of producing multiple transcriptions from overlapped speech. SOT has two advantages over PIT: (1) no limitation in the maximum number of speakers, and (2) an ability to mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12687","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/2003.12687/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":"2003.12687","created_at":"2026-07-05T01:25:37.634254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.12687v2","created_at":"2026-07-05T01:25:37.634254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12687","created_at":"2026-07-05T01:25:37.634254+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVK4FVMXFEWL","created_at":"2026-07-05T01:25:37.634254+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVK4FVMXFEWLTQUJ","created_at":"2026-07-05T01:25:37.634254+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVK4FVMX","created_at":"2026-07-05T01:25:37.634254+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/AVK4FVMXFEWLTQUJDRVSPM3FNJ","json":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ.json","graph_json":"https://pith.science/api/pith-number/AVK4FVMXFEWLTQUJDRVSPM3FNJ/graph.json","events_json":"https://pith.science/api/pith-number/AVK4FVMXFEWLTQUJDRVSPM3FNJ/events.json","paper":"https://pith.science/paper/AVK4FVMX"},"agent_actions":{"view_html":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ","download_json":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ.json","view_paper":"https://pith.science/paper/AVK4FVMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.12687&json=true","fetch_graph":"https://pith.science/api/pith-number/AVK4FVMXFEWLTQUJDRVSPM3FNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AVK4FVMXFEWLTQUJDRVSPM3FNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ/action/storage_attestation","attest_author":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ/action/author_attestation","sign_citation":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ/action/citation_signature","submit_replication":"https://pith.science/pith/AVK4FVMXFEWLTQUJDRVSPM3FNJ/action/replication_record"}},"created_at":"2026-07-05T01:25:37.634254+00:00","updated_at":"2026-07-05T01:25:37.634254+00:00"}