{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:KUDH62J7OY7J3TU3PWKIZCZRUA","short_pith_number":"pith:KUDH62J7","canonical_record":{"source":{"id":"2103.16776","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-31T02:43:32Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3f3f66459b291604f2387cc3b1b0ef6c1f18fb9185f0062b15e25654ec07ae2e","abstract_canon_sha256":"1ac3298bb3cd36021f5c0e033ea10149b0cd87d906a8512114ed7e17786df331"},"schema_version":"1.0"},"canonical_sha256":"55067f693f763e9dce9b7d948c8b31a0015ceadcf1ddbfe43da76937d36b3dd2","source":{"kind":"arxiv","id":"2103.16776","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16776","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16776v3","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16776","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"KUDH62J7OY7J","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"KUDH62J7OY7J3TU3","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"KUDH62J7","created_at":"2026-07-05T02:31:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:KUDH62J7OY7J3TU3PWKIZCZRUA","target":"record","payload":{"canonical_record":{"source":{"id":"2103.16776","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-31T02:43:32Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3f3f66459b291604f2387cc3b1b0ef6c1f18fb9185f0062b15e25654ec07ae2e","abstract_canon_sha256":"1ac3298bb3cd36021f5c0e033ea10149b0cd87d906a8512114ed7e17786df331"},"schema_version":"1.0"},"canonical_sha256":"55067f693f763e9dce9b7d948c8b31a0015ceadcf1ddbfe43da76937d36b3dd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:23.504301Z","signature_b64":"O86qJ4bjB0JJjwM1R7UbL6zgb/j84NaSTHYxe2du1DD1d4zZ2bzbnxK+4/9h+FSAW8/HnHdSPxQH6mslUv0hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55067f693f763e9dce9b7d948c8b31a0015ceadcf1ddbfe43da76937d36b3dd2","last_reissued_at":"2026-07-05T02:31:23.503823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:23.503823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.16776","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmQzEFxFxkF/FKQQBWjc/MFDBzgVpzuscDQc0oLUB7syw3OuflFqDMEaziuZ//olaGgL+b/CTM71b12B/mN9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:24:00.977446Z"},"content_sha256":"5ea18fd30a8b0824580966283e55c2b85d5c871d53470426e01a860d025c78af","schema_version":"1.0","event_id":"sha256:5ea18fd30a8b0824580966283e55c2b85d5c871d53470426e01a860d025c78af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:KUDH62J7OY7J3TU3PWKIZCZRUA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Guoli Ye, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Yashesh Gaur, Yu Wu, Zhong Meng, Zhuo Chen","submitted_at":"2021-03-31T02:43:32Z","abstract_excerpt":"Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous studies on the monaural overlapped speech recognition problem were based on either simulation data or small-scale real data. In this paper, we extensively investigate a two-step approach where we first pre-train a serialized output training (SOT)-based multi-talker ASR by using large-scale simulation data and then fine-tune the model with a small amount of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16776","kind":"arxiv","version":3},"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/2103.16776/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8GURqbW48uxWjxoqsJGaZdAdYOeGdEi7ap4E6xj1RkXH7yb8X1PlB7JWDx6QedsawHt10deGWc6c54u87n7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:24:00.978282Z"},"content_sha256":"182acd450724bb3a93a496680783b6f7c172d9b5ca213719e117b9cf76152d89","schema_version":"1.0","event_id":"sha256:182acd450724bb3a93a496680783b6f7c172d9b5ca213719e117b9cf76152d89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUDH62J7OY7J3TU3PWKIZCZRUA/bundle.json","state_url":"https://pith.science/pith/KUDH62J7OY7J3TU3PWKIZCZRUA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUDH62J7OY7J3TU3PWKIZCZRUA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:24:00Z","links":{"resolver":"https://pith.science/pith/KUDH62J7OY7J3TU3PWKIZCZRUA","bundle":"https://pith.science/pith/KUDH62J7OY7J3TU3PWKIZCZRUA/bundle.json","state":"https://pith.science/pith/KUDH62J7OY7J3TU3PWKIZCZRUA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUDH62J7OY7J3TU3PWKIZCZRUA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KUDH62J7OY7J3TU3PWKIZCZRUA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1ac3298bb3cd36021f5c0e033ea10149b0cd87d906a8512114ed7e17786df331","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-31T02:43:32Z","title_canon_sha256":"3f3f66459b291604f2387cc3b1b0ef6c1f18fb9185f0062b15e25654ec07ae2e"},"schema_version":"1.0","source":{"id":"2103.16776","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16776","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16776v3","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16776","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"KUDH62J7OY7J","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"KUDH62J7OY7J3TU3","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"KUDH62J7","created_at":"2026-07-05T02:31:23Z"}],"graph_snapshots":[{"event_id":"sha256:182acd450724bb3a93a496680783b6f7c172d9b5ca213719e117b9cf76152d89","target":"graph","created_at":"2026-07-05T02:31:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.16776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous studies on the monaural overlapped speech recognition problem were based on either simulation data or small-scale real data. In this paper, we extensively investigate a two-step approach where we first pre-train a serialized output training (SOT)-based multi-talker ASR by using large-scale simulation data and then fine-tune the model with a small amount of re","authors_text":"Guoli Ye, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Yashesh Gaur, Yu Wu, Zhong Meng, Zhuo Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-31T02:43:32Z","title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16776","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5ea18fd30a8b0824580966283e55c2b85d5c871d53470426e01a860d025c78af","target":"record","created_at":"2026-07-05T02:31:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1ac3298bb3cd36021f5c0e033ea10149b0cd87d906a8512114ed7e17786df331","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-31T02:43:32Z","title_canon_sha256":"3f3f66459b291604f2387cc3b1b0ef6c1f18fb9185f0062b15e25654ec07ae2e"},"schema_version":"1.0","source":{"id":"2103.16776","kind":"arxiv","version":3}},"canonical_sha256":"55067f693f763e9dce9b7d948c8b31a0015ceadcf1ddbfe43da76937d36b3dd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55067f693f763e9dce9b7d948c8b31a0015ceadcf1ddbfe43da76937d36b3dd2","first_computed_at":"2026-07-05T02:31:23.503823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:23.503823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O86qJ4bjB0JJjwM1R7UbL6zgb/j84NaSTHYxe2du1DD1d4zZ2bzbnxK+4/9h+FSAW8/HnHdSPxQH6mslUv0hDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:23.504301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.16776","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ea18fd30a8b0824580966283e55c2b85d5c871d53470426e01a860d025c78af","sha256:182acd450724bb3a93a496680783b6f7c172d9b5ca213719e117b9cf76152d89"],"state_sha256":"ae529efa5ec3f673f61b5997e19882810fadacc6dc33ffe7cf379f16b868c8ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnilnmijkmV/j1GcQAVGntHiDEQlaZuRNjW5HD1iZvrqA0vCmNmLxOVrlcl8o8eDq2ESAoDkoRcBRv9IfEf9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:24:00.996522Z","bundle_sha256":"432ffcfbb1a7ece4b5c17de52a43078c5adc15522b24ca40e4ae859083c31460"}}