{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7SMNMVJCZIILXIOGGZW3752UKW","short_pith_number":"pith:7SMNMVJC","schema_version":"1.0","canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","source":{"kind":"arxiv","id":"2604.03219","version":2},"attestation_state":"computed","paper":{"title":"Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dhruv Jain, Hao-Wen Dong, Meysam Asgari, Sidharth Sidharth","submitted_at":"2026-04-03T17:46:17Z","abstract_excerpt":"We study whether persistent conversational speaker structure can be extracted directly from local overlapping speech mixtures. We propose a teacher-student framework that learns mixture-derived multi-speaker embeddings using only short overlapping segments and permutation-invariant latent supervision. Despite never being explicitly trained for speaker tracking, diarization, or conversational memory, the learned embedding space supports long-form speaker re-identification when combined with a lightweight online memory mechanism during inference. We additionally observe that the learned represen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2604.03219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-03T17:46:17Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1d3460bf8a729aa28105543e7f3dc9b44465459ff32c8630a63adf8a3c5de4e1","abstract_canon_sha256":"798069f89262b5ca4208d8fd28fa522cc6a59da69c749feda774f07e9d57db94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:23.339368Z","signature_b64":"NrhKRiNBYjem3sPQAg37WPcjEqUvh3rXYN/WO5r8W2SFL6ZBWkXyZvMS3ojY+B0uve5Dy952Xa56n2YBsRf6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc98d65522ca10bba1c6366dbff754558142ab46f40bb98d03930cc1e27c06ac","last_reissued_at":"2026-06-23T02:13:23.339025Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:23.339025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dhruv Jain, Hao-Wen Dong, Meysam Asgari, Sidharth Sidharth","submitted_at":"2026-04-03T17:46:17Z","abstract_excerpt":"We study whether persistent conversational speaker structure can be extracted directly from local overlapping speech mixtures. We propose a teacher-student framework that learns mixture-derived multi-speaker embeddings using only short overlapping segments and permutation-invariant latent supervision. Despite never being explicitly trained for speaker tracking, diarization, or conversational memory, the learned embedding space supports long-form speaker re-identification when combined with a lightweight online memory mechanism during inference. We additionally observe that the learned represen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d931b6c47b39b46cc54836b5e23e8ea88d5f77de79c43d5d3e2d4ea1b0c03a6"},"source":{"id":"2604.03219","kind":"arxiv","version":2},"verdict":{"id":"dca9a624-37ed-4531-9bc3-e2253a3f4d48","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T17:55:23.394562Z","strongest_claim":"Our model maps a noisy mixture directly to a small set of candidate speaker embeddings trained to align with a strong single-speaker speaker-embedding space via permutation-invariant teacher supervision.","one_line_summary":"A neural model predicts a set of speaker embeddings from noisy mixtures to enable enrollment-free target speech extraction, outperforming baselines on LibriMix and generalizing to real recordings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embeddings predicted from the mixture alone will align sufficiently with the single-speaker embedding space to serve as effective control signals for downstream extraction without any enrollment data.","pith_extraction_headline":"A model learns to predict speaker embeddings directly from noisy mixtures, enabling target speech extraction without any enrollment recording."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03219/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":2,"snapshot_sha256":"765ffad865f890138bd07d1f47f356460c202d5f18f5bcaddf5114ae196d83cb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.03219","created_at":"2026-06-23T02:13:23.339071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.03219v2","created_at":"2026-06-23T02:13:23.339071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03219","created_at":"2026-06-23T02:13:23.339071+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SMNMVJCZIIL","created_at":"2026-06-23T02:13:23.339071+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SMNMVJCZIILXIOG","created_at":"2026-06-23T02:13:23.339071+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SMNMVJC","created_at":"2026-06-23T02:13:23.339071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.03219","citing_title":"Unmixing The Crowd: Learning Persistent Speaker Representations from Mixture-Derived Multi-Speaker Embeddings","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW","json":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW.json","graph_json":"https://pith.science/api/pith-number/7SMNMVJCZIILXIOGGZW3752UKW/graph.json","events_json":"https://pith.science/api/pith-number/7SMNMVJCZIILXIOGGZW3752UKW/events.json","paper":"https://pith.science/paper/7SMNMVJC"},"agent_actions":{"view_html":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW","download_json":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW.json","view_paper":"https://pith.science/paper/7SMNMVJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.03219&json=true","fetch_graph":"https://pith.science/api/pith-number/7SMNMVJCZIILXIOGGZW3752UKW/graph.json","fetch_events":"https://pith.science/api/pith-number/7SMNMVJCZIILXIOGGZW3752UKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/action/storage_attestation","attest_author":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/action/author_attestation","sign_citation":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/action/citation_signature","submit_replication":"https://pith.science/pith/7SMNMVJCZIILXIOGGZW3752UKW/action/replication_record"}},"created_at":"2026-06-23T02:13:23.339071+00:00","updated_at":"2026-06-23T02:13:23.339071+00:00"}