{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3CDF2R2R4VIK4KQGQGECRZSLJM","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":"4f0dfce4410c8cedbe7d100a9322cb44076b1b0742b17f449fa1322769b6a6a3","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-21T14:38:20Z","title_canon_sha256":"8bc1a3d33d6f5d7ed5d8362afffd61afbd9fc753d2193292061162b8441b5a42"},"schema_version":"1.0","source":{"id":"2410.16059","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16059","created_at":"2026-07-05T09:47:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16059v2","created_at":"2026-07-05T09:47:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16059","created_at":"2026-07-05T09:47:35Z"},{"alias_kind":"pith_short_12","alias_value":"3CDF2R2R4VIK","created_at":"2026-07-05T09:47:35Z"},{"alias_kind":"pith_short_16","alias_value":"3CDF2R2R4VIK4KQG","created_at":"2026-07-05T09:47:35Z"},{"alias_kind":"pith_short_8","alias_value":"3CDF2R2R","created_at":"2026-07-05T09:47:35Z"}],"graph_snapshots":[{"event_id":"sha256:c9a55b55e8fb3967cb765842533470249e88f9a8d5231214a03e6f7310d6ec72","target":"graph","created_at":"2026-07-05T09:47:35Z","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/2410.16059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model'","authors_text":"Haizhou Li, Junjie Li, Ke Zhang, Shuai Wang, Yangjie Wei, Yannan Wang, Yi Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-21T14:38:20Z","title":"Multi-Level Speaker Representation for Target Speaker Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16059","kind":"arxiv","version":2},"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":"sha256:1c2b05043e3d10ac4e78a902dfc76c1b6c1729c3ba239f9a22af5d6652378a6c","target":"record","created_at":"2026-07-05T09:47:35Z","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":"4f0dfce4410c8cedbe7d100a9322cb44076b1b0742b17f449fa1322769b6a6a3","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-21T14:38:20Z","title_canon_sha256":"8bc1a3d33d6f5d7ed5d8362afffd61afbd9fc753d2193292061162b8441b5a42"},"schema_version":"1.0","source":{"id":"2410.16059","kind":"arxiv","version":2}},"canonical_sha256":"d8865d4751e550ae2a06818828e64b4b25b8052af1a97900027326de586f4f09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8865d4751e550ae2a06818828e64b4b25b8052af1a97900027326de586f4f09","first_computed_at":"2026-07-05T09:47:35.618952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:35.618952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W5uuDUIj99E/1tSgNptoJWCxzj+ykIx8yFgipXxJC7zU9lTQTgclGhma2XgHUWF9IfZZc8WHmk20dDRMIJ+eDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:35.619517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16059","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c2b05043e3d10ac4e78a902dfc76c1b6c1729c3ba239f9a22af5d6652378a6c","sha256:c9a55b55e8fb3967cb765842533470249e88f9a8d5231214a03e6f7310d6ec72"],"state_sha256":"275bb593b9901b675c41f7c571a8265c968a538b7d0a990e7dc7f0d7b0e6de5f"}