{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HV2IICLOF7WTMP5TKECFHOHUGN","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":"3c55b19a342270e8c555f47527c291b3735a4825b10b15c5fc3b1352b646ed9d","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T08:41:07Z","title_canon_sha256":"d0ccc253c4d44112ea69c051149a3978c4b746bacabcf50f71c9cc18aefbe947"},"schema_version":"1.0","source":{"id":"2409.07841","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07841","created_at":"2026-07-05T09:07:51Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07841v3","created_at":"2026-07-05T09:07:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07841","created_at":"2026-07-05T09:07:51Z"},{"alias_kind":"pith_short_12","alias_value":"HV2IICLOF7WT","created_at":"2026-07-05T09:07:51Z"},{"alias_kind":"pith_short_16","alias_value":"HV2IICLOF7WTMP5T","created_at":"2026-07-05T09:07:51Z"},{"alias_kind":"pith_short_8","alias_value":"HV2IICLO","created_at":"2026-07-05T09:07:51Z"}],"graph_snapshots":[{"event_id":"sha256:544e4e42bf999d4d9afcfe1acd75c12df5f75471f35b9b0c9f5b24c84376e37e","target":"graph","created_at":"2026-07-05T09:07:51Z","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/2409.07841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. E","authors_text":"Bang Zeng, Beilong Tang, Ming Li","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T08:41:07Z","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07841","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":"sha256:817fe3990d19c121447ceccb3b6cfe42b57e42401ecba0044cf4133cea59b802","target":"record","created_at":"2026-07-05T09:07:51Z","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":"3c55b19a342270e8c555f47527c291b3735a4825b10b15c5fc3b1352b646ed9d","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-12T08:41:07Z","title_canon_sha256":"d0ccc253c4d44112ea69c051149a3978c4b746bacabcf50f71c9cc18aefbe947"},"schema_version":"1.0","source":{"id":"2409.07841","kind":"arxiv","version":3}},"canonical_sha256":"3d7484096e2fed363fb3510453b8f4337b200a47e221e5cdb10ae0d2a8791f0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d7484096e2fed363fb3510453b8f4337b200a47e221e5cdb10ae0d2a8791f0e","first_computed_at":"2026-07-05T09:07:51.214053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:51.214053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/GzktnzI3y4lBidAXjJIBcRRVE5OK8AzSJq2lJU8e0VVkc1ZyPA1bLAzSOhe4ANe2fl5rcXbMDynDFItQhiFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:51.214498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07841","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:817fe3990d19c121447ceccb3b6cfe42b57e42401ecba0044cf4133cea59b802","sha256:544e4e42bf999d4d9afcfe1acd75c12df5f75471f35b9b0c9f5b24c84376e37e"],"state_sha256":"4543b29db0fb1c5eb40f3573b98cfeeab815a9b80b033feb14250389d5de4f0a"}