{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZDGYNS6QYIGUBT4DYVKBYFK4ON","short_pith_number":"pith:ZDGYNS6Q","canonical_record":{"source":{"id":"2505.10975","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T08:21:59Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e6528eab19210af212f8ec5b3a8ff8047947fd4ba77e70a03b5c71c80426dd74","abstract_canon_sha256":"ad01784be71fc4a75a19fff3cdedf170a92f640c7070e826a75a5935ee94a9a5"},"schema_version":"1.0"},"canonical_sha256":"c8cd86cbd0c20d40cf83c5541c155c7371ba0a03fffaf3143c1e9e9a3124a8cd","source":{"kind":"arxiv","id":"2505.10975","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10975","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10975v3","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10975","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZDGYNS6QYIGU","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZDGYNS6QYIGUBT4D","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZDGYNS6Q","created_at":"2026-05-29T01:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZDGYNS6QYIGUBT4DYVKBYFK4ON","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10975","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T08:21:59Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"e6528eab19210af212f8ec5b3a8ff8047947fd4ba77e70a03b5c71c80426dd74","abstract_canon_sha256":"ad01784be71fc4a75a19fff3cdedf170a92f640c7070e826a75a5935ee94a9a5"},"schema_version":"1.0"},"canonical_sha256":"c8cd86cbd0c20d40cf83c5541c155c7371ba0a03fffaf3143c1e9e9a3124a8cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:53.257108Z","signature_b64":"DgXKgh8NBovhMrd53P+jSsNj0Q8vDQxF43Apf1d3qNPHaE8pZOTOp7yxJX+nSIi9ASbJh/TS7v1hhyuf4bK5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8cd86cbd0c20d40cf83c5541c155c7371ba0a03fffaf3143c1e9e9a3124a8cd","last_reissued_at":"2026-05-29T01:04:53.256639Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:53.256639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10975","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":"2026-05-29T01:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pa31yEjkuPmNGgGwFhMw7D6JqbmTCvk2IzX9CUP/Yjzfb2DRX8/pVK7HlksdJbrEY7IZvrZREbwGyBf1iHiSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:49:34.141099Z"},"content_sha256":"148c3ad50a8a7f922b21dc8f80eda0afb1f50b9a8cf6f18a6b845eddf3e57fdb","schema_version":"1.0","event_id":"sha256:148c3ad50a8a7f922b21dc8f80eda0afb1f50b9a8cf6f18a6b845eddf3e57fdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZDGYNS6QYIGUBT4DYVKBYFK4ON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jacob Whitehill, Xinlu He","submitted_at":"2025-05-16T08:21:59Z","abstract_excerpt":"Monaural multi-speaker automatic speech recognition (ASR) remains challenging due to data scarcity and the intrinsic difficulty of recognizing and attributing words to individual speakers, particularly in overlapping speech. Recent advances have driven the shift from cascade systems to end-to-end (E2E) architectures, which reduce error propagation and better exploit the synergy between speech content and speaker identity. Despite rapid progress in E2E multi-speaker ASR, the field lacks a comprehensive review of recent developments. This survey provides a systematic taxonomy of E2E neural appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10975","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/2505.10975/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":"2026-05-29T01:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yV9zIMs6idRdHysZn9Y6tqtRKKuP9E+hyokV2bnVBIjO/6gM9/q9OWknWWpLYGUToi2FHS9LxwDr/NRi+rI5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:49:34.141595Z"},"content_sha256":"92c5fe361da081b32dda0ed60a835ec6d2e994f6e8b44ec926f6d4346e5c5929","schema_version":"1.0","event_id":"sha256:92c5fe361da081b32dda0ed60a835ec6d2e994f6e8b44ec926f6d4346e5c5929"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON/bundle.json","state_url":"https://pith.science/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON/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":"2026-08-09T23:49:34Z","links":{"resolver":"https://pith.science/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON","bundle":"https://pith.science/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON/bundle.json","state":"https://pith.science/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDGYNS6QYIGUBT4DYVKBYFK4ON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZDGYNS6QYIGUBT4DYVKBYFK4ON","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":"ad01784be71fc4a75a19fff3cdedf170a92f640c7070e826a75a5935ee94a9a5","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T08:21:59Z","title_canon_sha256":"e6528eab19210af212f8ec5b3a8ff8047947fd4ba77e70a03b5c71c80426dd74"},"schema_version":"1.0","source":{"id":"2505.10975","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10975","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10975v3","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10975","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZDGYNS6QYIGU","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZDGYNS6QYIGUBT4D","created_at":"2026-05-29T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZDGYNS6Q","created_at":"2026-05-29T01:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:92c5fe361da081b32dda0ed60a835ec6d2e994f6e8b44ec926f6d4346e5c5929","target":"graph","created_at":"2026-05-29T01:04:53Z","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/2505.10975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monaural multi-speaker automatic speech recognition (ASR) remains challenging due to data scarcity and the intrinsic difficulty of recognizing and attributing words to individual speakers, particularly in overlapping speech. Recent advances have driven the shift from cascade systems to end-to-end (E2E) architectures, which reduce error propagation and better exploit the synergy between speech content and speaker identity. Despite rapid progress in E2E multi-speaker ASR, the field lacks a comprehensive review of recent developments. This survey provides a systematic taxonomy of E2E neural appro","authors_text":"Jacob Whitehill, Xinlu He","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T08:21:59Z","title":"Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10975","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":"sha256:148c3ad50a8a7f922b21dc8f80eda0afb1f50b9a8cf6f18a6b845eddf3e57fdb","target":"record","created_at":"2026-05-29T01:04:53Z","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":"ad01784be71fc4a75a19fff3cdedf170a92f640c7070e826a75a5935ee94a9a5","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T08:21:59Z","title_canon_sha256":"e6528eab19210af212f8ec5b3a8ff8047947fd4ba77e70a03b5c71c80426dd74"},"schema_version":"1.0","source":{"id":"2505.10975","kind":"arxiv","version":3}},"canonical_sha256":"c8cd86cbd0c20d40cf83c5541c155c7371ba0a03fffaf3143c1e9e9a3124a8cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8cd86cbd0c20d40cf83c5541c155c7371ba0a03fffaf3143c1e9e9a3124a8cd","first_computed_at":"2026-05-29T01:04:53.256639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:53.256639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DgXKgh8NBovhMrd53P+jSsNj0Q8vDQxF43Apf1d3qNPHaE8pZOTOp7yxJX+nSIi9ASbJh/TS7v1hhyuf4bK5BQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:53.257108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10975","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:148c3ad50a8a7f922b21dc8f80eda0afb1f50b9a8cf6f18a6b845eddf3e57fdb","sha256:92c5fe361da081b32dda0ed60a835ec6d2e994f6e8b44ec926f6d4346e5c5929"],"state_sha256":"9d3b52d44fee938aed7ec3fd921675515ec6e67a172bb692da3ede6b16177ab8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjT1Y1lTls62HJ5rmgChR4cvBi+5ClDk7ZUss/jFwYG+rd/NGuSM23e26Wnq25tNNUQ6c6XrG3Rzpw0P7CUqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:49:34.146773Z","bundle_sha256":"94cd46739cbfcf9ee45beebce6a9fdcc859018dd541c70e26331be236035d53d"}}