{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QCKEVDNEYI6INVTPNQTUXGVNGO","short_pith_number":"pith:QCKEVDNE","schema_version":"1.0","canonical_sha256":"80944a8da4c23c86d66f6c274b9aad33917949ce58dfa0bffa7c561822732551","source":{"kind":"arxiv","id":"2411.18497","version":1},"attestation_state":"computed","paper":{"title":"Multiple Choice Learning for Efficient Speech Separation with Many Speakers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"David Perera, Fran\\c{c}ois Derrida, Ga\\\"el Richard, Slim Essid, Th\\'eo Mariotte","submitted_at":"2024-11-27T16:38:34Z","abstract_excerpt":"Training speech separation models in the supervised setting raises a permutation problem: finding the best assignation between the model predictions and the ground truth separated signals. This inherently ambiguous task is customarily solved using Permutation Invariant Training (PIT). In this article, we instead consider using the Multiple Choice Learning (MCL) framework, which was originally introduced to tackle ambiguous tasks. We demonstrate experimentally on the popular WSJ0-mix and LibriMix benchmarks that MCL matches the performances of PIT, while being computationally advantageous. This"},"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":false},"canonical_record":{"source":{"id":"2411.18497","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-27T16:38:34Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"4ef1c4ece420ff89c1a26207b11fdf5e3d30f96e3ff28114400a523fb1c3dc09","abstract_canon_sha256":"9304e19ecd5953d9840bba7f22434a2e39f22f7f20745981a1eab40c7bae0c82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:17.258571Z","signature_b64":"4K0EPaSUCDvar/HMptGhZKu7vEznS5Rgo3+IZxFroWxISQ0ZgrheoQNHKikJTqVabzX9dbIWyM8u4+qDm715Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80944a8da4c23c86d66f6c274b9aad33917949ce58dfa0bffa7c561822732551","last_reissued_at":"2026-07-05T09:41:17.258153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:17.258153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple Choice Learning for Efficient Speech Separation with Many Speakers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"David Perera, Fran\\c{c}ois Derrida, Ga\\\"el Richard, Slim Essid, Th\\'eo Mariotte","submitted_at":"2024-11-27T16:38:34Z","abstract_excerpt":"Training speech separation models in the supervised setting raises a permutation problem: finding the best assignation between the model predictions and the ground truth separated signals. This inherently ambiguous task is customarily solved using Permutation Invariant Training (PIT). In this article, we instead consider using the Multiple Choice Learning (MCL) framework, which was originally introduced to tackle ambiguous tasks. We demonstrate experimentally on the popular WSJ0-mix and LibriMix benchmarks that MCL matches the performances of PIT, while being computationally advantageous. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18497","kind":"arxiv","version":1},"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/2411.18497/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.18497","created_at":"2026-07-05T09:41:17.258212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18497v1","created_at":"2026-07-05T09:41:17.258212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18497","created_at":"2026-07-05T09:41:17.258212+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCKEVDNEYI6I","created_at":"2026-07-05T09:41:17.258212+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCKEVDNEYI6INVTP","created_at":"2026-07-05T09:41:17.258212+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCKEVDNE","created_at":"2026-07-05T09:41:17.258212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO","json":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO.json","graph_json":"https://pith.science/api/pith-number/QCKEVDNEYI6INVTPNQTUXGVNGO/graph.json","events_json":"https://pith.science/api/pith-number/QCKEVDNEYI6INVTPNQTUXGVNGO/events.json","paper":"https://pith.science/paper/QCKEVDNE"},"agent_actions":{"view_html":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO","download_json":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO.json","view_paper":"https://pith.science/paper/QCKEVDNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18497&json=true","fetch_graph":"https://pith.science/api/pith-number/QCKEVDNEYI6INVTPNQTUXGVNGO/graph.json","fetch_events":"https://pith.science/api/pith-number/QCKEVDNEYI6INVTPNQTUXGVNGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO/action/storage_attestation","attest_author":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO/action/author_attestation","sign_citation":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO/action/citation_signature","submit_replication":"https://pith.science/pith/QCKEVDNEYI6INVTPNQTUXGVNGO/action/replication_record"}},"created_at":"2026-07-05T09:41:17.258212+00:00","updated_at":"2026-07-05T09:41:17.258212+00:00"}