{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H3SMHE4CX6QXZHWS67ZZ4JK6MV","short_pith_number":"pith:H3SMHE4C","schema_version":"1.0","canonical_sha256":"3ee4c39382bfa17c9ed2f7f39e255e65639baf54f073589d55fd8d94e6aff38b","source":{"kind":"arxiv","id":"2406.17722","version":1},"attestation_state":"computed","paper":{"title":"Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Kanami Imamura, Kentaro Seki, Norihiro Takamune, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2024-06-25T17:10:39Z","abstract_excerpt":"This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice conversion methods focus on single-channel waveforms, ignoring the stereo listening experience inherent in human hearing. Our baseline approach addresses this gap by integrating blind source separation (BSS), voice conversion (VC), and spatial mixing to handle multi-channel waveforms. Through experimental evaluations, we organize and identify the key challenges inherent in this task, such as maintaining audio quality"},"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":"2406.17722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T17:10:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e9cebe2dd14ad009735b3c2229e48f611425ad15e9fb33802199b180a0bdeff6","abstract_canon_sha256":"12d7405d7f61296739fdc4c3f2ab00e110ae017dd546862e0fc05f7ade6ba890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:39.128460Z","signature_b64":"wNC6UNkzOc0Qm+rTYzjG1x7ElVkwJW8JRcUhZ0Ba4loZmqnvVvRma2erz2b95kNqR/5wM1+wW46zgZ8qCTiCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee4c39382bfa17c9ed2f7f39e255e65639baf54f073589d55fd8d94e6aff38b","last_reissued_at":"2026-07-05T08:36:39.128006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:39.128006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Kanami Imamura, Kentaro Seki, Norihiro Takamune, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2024-06-25T17:10:39Z","abstract_excerpt":"This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice conversion methods focus on single-channel waveforms, ignoring the stereo listening experience inherent in human hearing. Our baseline approach addresses this gap by integrating blind source separation (BSS), voice conversion (VC), and spatial mixing to handle multi-channel waveforms. Through experimental evaluations, we organize and identify the key challenges inherent in this task, such as maintaining audio quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17722","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/2406.17722/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":"2406.17722","created_at":"2026-07-05T08:36:39.128062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17722v1","created_at":"2026-07-05T08:36:39.128062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17722","created_at":"2026-07-05T08:36:39.128062+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3SMHE4CX6QX","created_at":"2026-07-05T08:36:39.128062+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3SMHE4CX6QXZHWS","created_at":"2026-07-05T08:36:39.128062+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3SMHE4C","created_at":"2026-07-05T08:36:39.128062+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/H3SMHE4CX6QXZHWS67ZZ4JK6MV","json":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV.json","graph_json":"https://pith.science/api/pith-number/H3SMHE4CX6QXZHWS67ZZ4JK6MV/graph.json","events_json":"https://pith.science/api/pith-number/H3SMHE4CX6QXZHWS67ZZ4JK6MV/events.json","paper":"https://pith.science/paper/H3SMHE4C"},"agent_actions":{"view_html":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV","download_json":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV.json","view_paper":"https://pith.science/paper/H3SMHE4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17722&json=true","fetch_graph":"https://pith.science/api/pith-number/H3SMHE4CX6QXZHWS67ZZ4JK6MV/graph.json","fetch_events":"https://pith.science/api/pith-number/H3SMHE4CX6QXZHWS67ZZ4JK6MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV/action/storage_attestation","attest_author":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV/action/author_attestation","sign_citation":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV/action/citation_signature","submit_replication":"https://pith.science/pith/H3SMHE4CX6QXZHWS67ZZ4JK6MV/action/replication_record"}},"created_at":"2026-07-05T08:36:39.128062+00:00","updated_at":"2026-07-05T08:36:39.128062+00:00"}