{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7CWB63TKKS26ZJ2T6Z3BCPG6FJ","short_pith_number":"pith:7CWB63TK","canonical_record":{"source":{"id":"2104.02109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-05T18:37:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc82fad555a661232a44659e0c0afad9845c059a59b3de6b04b1ed670a34f15a","abstract_canon_sha256":"51142966228ee8a49b3b6d8783e7e14a79a7373f6643489620e03ad8eb2b1a89"},"schema_version":"1.0"},"canonical_sha256":"f8ac1f6e6a54b5eca753f676113cde2a54ebfa98e608e86c9cdd271d412d288f","source":{"kind":"arxiv","id":"2104.02109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02109","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02109v1","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02109","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"7CWB63TKKS26","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"7CWB63TKKS26ZJ2T","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"7CWB63TK","created_at":"2026-07-05T02:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7CWB63TKKS26ZJ2T6Z3BCPG6FJ","target":"record","payload":{"canonical_record":{"source":{"id":"2104.02109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-05T18:37:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc82fad555a661232a44659e0c0afad9845c059a59b3de6b04b1ed670a34f15a","abstract_canon_sha256":"51142966228ee8a49b3b6d8783e7e14a79a7373f6643489620e03ad8eb2b1a89"},"schema_version":"1.0"},"canonical_sha256":"f8ac1f6e6a54b5eca753f676113cde2a54ebfa98e608e86c9cdd271d412d288f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:14.016862Z","signature_b64":"GJ/UmMovLZzR+gp6xEhkWbgZFq8Sv0tyd6MLr202XrqHBauilXfcryy5o3R7av5KywE9er7MFphM2nR4WuKrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8ac1f6e6a54b5eca753f676113cde2a54ebfa98e608e86c9cdd271d412d288f","last_reissued_at":"2026-07-05T02:29:14.016353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:14.016353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.02109","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:29:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fjLmtV0V95oVx/ENl7LPhWa8lRsD8iZL2Rjy4aqr7ZdFsZ92diSu/8wIpv7RkiDLVPwJ6LYul27+3uqzFMakAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:50:01.670256Z"},"content_sha256":"8a4bcffaac8c26904cb02f44d02ab6b9da5eece60c4424a8f4e2b76d0d8fc0a5","schema_version":"1.0","event_id":"sha256:8a4bcffaac8c26904cb02f44d02ab6b9da5eece60c4424a8f4e2b76d0d8fc0a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7CWB63TKKS26ZJ2T6Z3BCPG6FJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streaming Multi-talker Speech Recognition with Joint Speaker Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Jinyu Li, Liang Lu, Naoyuki Kanda, Yifan Gong","submitted_at":"2021-04-05T18:37:33Z","abstract_excerpt":"In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this case, conventional approaches usually address this problem in a cascaded fashion that involves speech separation, speech recognition and speaker identification that are trained independently. In this paper, we propose Streaming Unmixing, Recognition and Identification Transducer (SURIT) -- a new framework that deals with this problem in an end-to-end streaming "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02109","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/2104.02109/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":"2026-07-05T02:29:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sUmdPDEw1awWMwRCSVMRHtLqhEy6/LHUX/+mr1IKNORO2ch3XEF7G2ReX+uT9stIpv1GAo1DTd+Pjfg/uNKeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:50:01.670646Z"},"content_sha256":"79d8adfea7a5fac590f9ceac850e77148090ec0ab3b8b3d214a9eecb668c1698","schema_version":"1.0","event_id":"sha256:79d8adfea7a5fac590f9ceac850e77148090ec0ab3b8b3d214a9eecb668c1698"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ/bundle.json","state_url":"https://pith.science/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ/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":"2026-08-05T00:50:01Z","links":{"resolver":"https://pith.science/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ","bundle":"https://pith.science/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ/bundle.json","state":"https://pith.science/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CWB63TKKS26ZJ2T6Z3BCPG6FJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7CWB63TKKS26ZJ2T6Z3BCPG6FJ","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":"51142966228ee8a49b3b6d8783e7e14a79a7373f6643489620e03ad8eb2b1a89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-05T18:37:33Z","title_canon_sha256":"fc82fad555a661232a44659e0c0afad9845c059a59b3de6b04b1ed670a34f15a"},"schema_version":"1.0","source":{"id":"2104.02109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02109","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02109v1","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02109","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"7CWB63TKKS26","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"7CWB63TKKS26ZJ2T","created_at":"2026-07-05T02:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"7CWB63TK","created_at":"2026-07-05T02:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:79d8adfea7a5fac590f9ceac850e77148090ec0ab3b8b3d214a9eecb668c1698","target":"graph","created_at":"2026-07-05T02:29:14Z","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/2104.02109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this case, conventional approaches usually address this problem in a cascaded fashion that involves speech separation, speech recognition and speaker identification that are trained independently. In this paper, we propose Streaming Unmixing, Recognition and Identification Transducer (SURIT) -- a new framework that deals with this problem in an end-to-end streaming ","authors_text":"Jinyu Li, Liang Lu, Naoyuki Kanda, Yifan Gong","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-05T18:37:33Z","title":"Streaming Multi-talker Speech Recognition with Joint Speaker Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02109","kind":"arxiv","version":1},"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":"sha256:8a4bcffaac8c26904cb02f44d02ab6b9da5eece60c4424a8f4e2b76d0d8fc0a5","target":"record","created_at":"2026-07-05T02:29:14Z","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":"51142966228ee8a49b3b6d8783e7e14a79a7373f6643489620e03ad8eb2b1a89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-05T18:37:33Z","title_canon_sha256":"fc82fad555a661232a44659e0c0afad9845c059a59b3de6b04b1ed670a34f15a"},"schema_version":"1.0","source":{"id":"2104.02109","kind":"arxiv","version":1}},"canonical_sha256":"f8ac1f6e6a54b5eca753f676113cde2a54ebfa98e608e86c9cdd271d412d288f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8ac1f6e6a54b5eca753f676113cde2a54ebfa98e608e86c9cdd271d412d288f","first_computed_at":"2026-07-05T02:29:14.016353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:14.016353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJ/UmMovLZzR+gp6xEhkWbgZFq8Sv0tyd6MLr202XrqHBauilXfcryy5o3R7av5KywE9er7MFphM2nR4WuKrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:14.016862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.02109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a4bcffaac8c26904cb02f44d02ab6b9da5eece60c4424a8f4e2b76d0d8fc0a5","sha256:79d8adfea7a5fac590f9ceac850e77148090ec0ab3b8b3d214a9eecb668c1698"],"state_sha256":"248f2eaec81f7b67b46f89ac5cb217843169a900909d7203be5cfe62d99f8fcf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XR/YDbP7PgZGKeTm0INJKgLdIADLWAsD7aMBZMcnr3RI4bv9eMluVpwRP7TWNQJ8j0xiMDdoogMrwUO22mVPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:50:01.673618Z","bundle_sha256":"10f8379f49e076eca3b7a52c67a886b012edd2c417cbfe2b6162adc92ce1737b"}}