{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BAHZQNREHT5TAIRKOKD3M5LMJ4","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":"f6206d8b6865637d6ecae1455aff4ab4fe545b27a8776244c1b94ce610c38467","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-27T22:21:58Z","title_canon_sha256":"c6106b7b0445a7b421a0c308a4c6f98f3f7b37029263e0e2501dfeeb7f98d8ef"},"schema_version":"1.0","source":{"id":"2505.21805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21805","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21805v1","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21805","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"BAHZQNREHT5T","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"BAHZQNREHT5TAIRK","created_at":"2026-07-05T11:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"BAHZQNRE","created_at":"2026-07-05T11:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:55d3e4857e1a6957df519be5f685dcfc445c68efdad5725197a951762dcfa2ac","target":"graph","created_at":"2026-07-05T11:11:03Z","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/2505.21805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target confusion, defined as occasional switching to non-target speakers, poses a key challenge for end-to-end speaker extraction (E2E-SE) systems. We argue that this problem is largely caused by the lack of generalizability and discrimination of the speaker embeddings, and introduce a simple yet effective speaker augmentation strategy to tackle the problem. Specifically, we propose a time-domain resampling and rescaling pipeline that alters speaker traits while preserving other speech properties. This generates a variety of pseudo-speakers to help establish a generalizable speaker embedding s","authors_text":"Dong Wang, Lantian Li, Zhenghai You, Zhenyu Zhou","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-27T22:21:58Z","title":"An Investigation on Speaker Augmentation for End-to-End Speaker Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21805","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":"sha256:8c885a10640079db7cf8c557fcdcec7aea9c70cf5718fb12d518ebba5c2b58f2","target":"record","created_at":"2026-07-05T11:11:03Z","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":"f6206d8b6865637d6ecae1455aff4ab4fe545b27a8776244c1b94ce610c38467","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-27T22:21:58Z","title_canon_sha256":"c6106b7b0445a7b421a0c308a4c6f98f3f7b37029263e0e2501dfeeb7f98d8ef"},"schema_version":"1.0","source":{"id":"2505.21805","kind":"arxiv","version":1}},"canonical_sha256":"080f9836243cfb30222a7287b6756c4f0ac7a4d0f6ebb1ce87a1fda1e1e907b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"080f9836243cfb30222a7287b6756c4f0ac7a4d0f6ebb1ce87a1fda1e1e907b5","first_computed_at":"2026-07-05T11:11:03.870270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:03.870270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ehSELscYf/h1vTlSQ42N21xO0SUdv+mwLTSIXX08V80rey2fBvBvjrIK9twl7DjSZq3wXttwhjEO9CuCFrrCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:03.870717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c885a10640079db7cf8c557fcdcec7aea9c70cf5718fb12d518ebba5c2b58f2","sha256:55d3e4857e1a6957df519be5f685dcfc445c68efdad5725197a951762dcfa2ac"],"state_sha256":"344f03a08a525ee2ac6ce7982c8690595cfa4e9a1bb95fad7bd42532286d174b"}