{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4MQ5WGPRPSMKVG4AO2HYJDH5XQ","short_pith_number":"pith:4MQ5WGPR","schema_version":"1.0","canonical_sha256":"e321db19f17c98aa9b80768f848cfdbc27938126a9a0c1a668febb79abcea0db","source":{"kind":"arxiv","id":"1906.09997","version":1},"attestation_state":"computed","paper":{"title":"Single-Channel Speech Separation with Auxiliary Speaker Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bj\\\"orn Schuller, Gil Keren, Shuo Liu","submitted_at":"2019-06-24T14:35:29Z","abstract_excerpt":"We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the ch"},"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":"1906.09997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T14:35:29Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"4ea198ffbb7688a1808ed71a6a18d34c5540ee5ebb5d3e6eb41f1e6d4a361946","abstract_canon_sha256":"ce0c31c934065ad6996c988b9e12b2d4eceb339fdc6e6caa3138d6ad2deee2f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:35.765531Z","signature_b64":"HweIhkoouxcUyUGiUWAy4Cqu/QYvoxkPs4Xp2cSrbKV4l1gBdNEerT6LwGDTWLx8hd83e1eQNRvI+54DT/mOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e321db19f17c98aa9b80768f848cfdbc27938126a9a0c1a668febb79abcea0db","last_reissued_at":"2026-05-17T23:42:35.764760Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:35.764760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-Channel Speech Separation with Auxiliary Speaker Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bj\\\"orn Schuller, Gil Keren, Shuo Liu","submitted_at":"2019-06-24T14:35:29Z","abstract_excerpt":"We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09997","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":""},"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":"1906.09997","created_at":"2026-05-17T23:42:35.764871+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09997v1","created_at":"2026-05-17T23:42:35.764871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09997","created_at":"2026-05-17T23:42:35.764871+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MQ5WGPRPSMK","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MQ5WGPRPSMKVG4A","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MQ5WGPR","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09997","citing_title":"Single-Channel Speech Separation with Auxiliary Speaker Embeddings","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ","json":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ.json","graph_json":"https://pith.science/api/pith-number/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/graph.json","events_json":"https://pith.science/api/pith-number/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/events.json","paper":"https://pith.science/paper/4MQ5WGPR"},"agent_actions":{"view_html":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ","download_json":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ.json","view_paper":"https://pith.science/paper/4MQ5WGPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09997&json=true","fetch_graph":"https://pith.science/api/pith-number/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/action/storage_attestation","attest_author":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/action/author_attestation","sign_citation":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/action/citation_signature","submit_replication":"https://pith.science/pith/4MQ5WGPRPSMKVG4AO2HYJDH5XQ/action/replication_record"}},"created_at":"2026-05-17T23:42:35.764871+00:00","updated_at":"2026-05-17T23:42:35.764871+00:00"}