{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U32FA6ZZT64EKOYVMMKVAFNU6W","short_pith_number":"pith:U32FA6ZZ","schema_version":"1.0","canonical_sha256":"a6f4507b399fb8453b1563155015b4f5b49843a411045e4ede7886bb48443332","source":{"kind":"arxiv","id":"2112.09382","version":2},"attestation_state":"computed","paper":{"title":"Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo Xu, Jing Shi, Shinji Watanabe, Tomoki Hayashi, Xuankai Chang, Yen-Ju Lu","submitted_at":"2021-12-17T08:35:40Z","abstract_excerpt":"Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression models to predict the ground-truth speech from the mixture, using the masking-based design and the signal-level loss criterion (e.g., MSE or SI-SNR). This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem, with great flexibility and strong potential. Specifically, we propose a novel speech separati"},"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":"2112.09382","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-17T08:35:40Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"bf808039f62e834742e09a4bdfea3eca7c35f1196947787eb13953df5708bb08","abstract_canon_sha256":"86069ace448a8a5379dc6bce5f4293bcf182046a3459585c5714322e55a8c718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:03.301552Z","signature_b64":"olb3tkmlJ/JYG0xppYfIBtAPM322vqFcxF/5S4vcllixrrKjdJjy+AYAhJD7zMxGLmdhL3IQvgNnSvjfSCSBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6f4507b399fb8453b1563155015b4f5b49843a411045e4ede7886bb48443332","last_reissued_at":"2026-07-05T03:47:03.301182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:03.301182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bo Xu, Jing Shi, Shinji Watanabe, Tomoki Hayashi, Xuankai Chang, Yen-Ju Lu","submitted_at":"2021-12-17T08:35:40Z","abstract_excerpt":"Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression models to predict the ground-truth speech from the mixture, using the masking-based design and the signal-level loss criterion (e.g., MSE or SI-SNR). This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem, with great flexibility and strong potential. Specifically, we propose a novel speech separati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09382","kind":"arxiv","version":2},"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/2112.09382/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":"2112.09382","created_at":"2026-07-05T03:47:03.301239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.09382v2","created_at":"2026-07-05T03:47:03.301239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09382","created_at":"2026-07-05T03:47:03.301239+00:00"},{"alias_kind":"pith_short_12","alias_value":"U32FA6ZZT64E","created_at":"2026-07-05T03:47:03.301239+00:00"},{"alias_kind":"pith_short_16","alias_value":"U32FA6ZZT64EKOYV","created_at":"2026-07-05T03:47:03.301239+00:00"},{"alias_kind":"pith_short_8","alias_value":"U32FA6ZZ","created_at":"2026-07-05T03:47:03.301239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17998","citing_title":"Speech Separation using Neural Audio Codecs with Embedding Loss","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W","json":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W.json","graph_json":"https://pith.science/api/pith-number/U32FA6ZZT64EKOYVMMKVAFNU6W/graph.json","events_json":"https://pith.science/api/pith-number/U32FA6ZZT64EKOYVMMKVAFNU6W/events.json","paper":"https://pith.science/paper/U32FA6ZZ"},"agent_actions":{"view_html":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W","download_json":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W.json","view_paper":"https://pith.science/paper/U32FA6ZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.09382&json=true","fetch_graph":"https://pith.science/api/pith-number/U32FA6ZZT64EKOYVMMKVAFNU6W/graph.json","fetch_events":"https://pith.science/api/pith-number/U32FA6ZZT64EKOYVMMKVAFNU6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W/action/storage_attestation","attest_author":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W/action/author_attestation","sign_citation":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W/action/citation_signature","submit_replication":"https://pith.science/pith/U32FA6ZZT64EKOYVMMKVAFNU6W/action/replication_record"}},"created_at":"2026-07-05T03:47:03.301239+00:00","updated_at":"2026-07-05T03:47:03.301239+00:00"}