{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MXJIEVZ4RFV5BJB7ORYZDTXX3Y","short_pith_number":"pith:MXJIEVZ4","schema_version":"1.0","canonical_sha256":"65d282573c896bd0a43f747191cef7de2fbd585bdd5bef453d342f761a2c7a76","source":{"kind":"arxiv","id":"2607.09043","version":1},"attestation_state":"computed","paper":{"title":"Technical Report for MERL's Real-TSE Challenge Submission","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Christoph Boeddeker, Dominik Klement, Gordon Wichern, Jonathan Le Roux, Julius Richter, Kohei Saijo, Yoshiki Masuyama","submitted_at":"2026-07-10T02:18:02Z","abstract_excerpt":"Target speech extraction (TSE) has largely been dominated by neural network-based approaches trained and evaluated on synthetic fully overlapped data. The Real-TSE Challenge aims to advance performance on real-world far-field noisy and reverberant recordings. This technical report describes MERL's submission to the Real-TSE Challenge. Rather than proposing a novel model architecture, we built upon the baseline model and focused primarily on data preparation and cleaning. Our system was trained in four stages, beginning with pre-training on fully overlapped mixtures and simulated multi-talker c"},"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":"2607.09043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-10T02:18:02Z","cross_cats_sorted":[],"title_canon_sha256":"7a0292679c61baf2871a99ea8cfac557f3a3bb1fe7febd0c5bf5706b57d765bc","abstract_canon_sha256":"e57bf7ef619d42f387b03ababf6e035b0dd6f41ea4a4bb71beab5184737ced10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:37.257930Z","signature_b64":"RVOtovoH4OmjfkIAw4rhgeYTwdECM4ZESQSwVehNdxkC8KMtLLtA3eJSfkq0+v/z0wpkBUT8tFbZwRXDV1wLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d282573c896bd0a43f747191cef7de2fbd585bdd5bef453d342f761a2c7a76","last_reissued_at":"2026-07-13T00:17:37.256470Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:37.256470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Technical Report for MERL's Real-TSE Challenge Submission","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Christoph Boeddeker, Dominik Klement, Gordon Wichern, Jonathan Le Roux, Julius Richter, Kohei Saijo, Yoshiki Masuyama","submitted_at":"2026-07-10T02:18:02Z","abstract_excerpt":"Target speech extraction (TSE) has largely been dominated by neural network-based approaches trained and evaluated on synthetic fully overlapped data. The Real-TSE Challenge aims to advance performance on real-world far-field noisy and reverberant recordings. This technical report describes MERL's submission to the Real-TSE Challenge. Rather than proposing a novel model architecture, we built upon the baseline model and focused primarily on data preparation and cleaning. Our system was trained in four stages, beginning with pre-training on fully overlapped mixtures and simulated multi-talker c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09043","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/2607.09043/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":"2607.09043","created_at":"2026-07-13T00:17:37.257193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09043v1","created_at":"2026-07-13T00:17:37.257193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09043","created_at":"2026-07-13T00:17:37.257193+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXJIEVZ4RFV5","created_at":"2026-07-13T00:17:37.257193+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXJIEVZ4RFV5BJB7","created_at":"2026-07-13T00:17:37.257193+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXJIEVZ4","created_at":"2026-07-13T00:17:37.257193+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/MXJIEVZ4RFV5BJB7ORYZDTXX3Y","json":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y.json","graph_json":"https://pith.science/api/pith-number/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/graph.json","events_json":"https://pith.science/api/pith-number/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/events.json","paper":"https://pith.science/paper/MXJIEVZ4"},"agent_actions":{"view_html":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y","download_json":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y.json","view_paper":"https://pith.science/paper/MXJIEVZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09043&json=true","fetch_graph":"https://pith.science/api/pith-number/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/action/storage_attestation","attest_author":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/action/author_attestation","sign_citation":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/action/citation_signature","submit_replication":"https://pith.science/pith/MXJIEVZ4RFV5BJB7ORYZDTXX3Y/action/replication_record"}},"created_at":"2026-07-13T00:17:37.257193+00:00","updated_at":"2026-07-13T00:17:37.257193+00:00"}