{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZMRMQ5RS5YJZHUDVM5EAONMADZ","short_pith_number":"pith:ZMRMQ5RS","canonical_record":{"source":{"id":"2306.10521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-18T10:59:06Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"46f7552b0ab409d85559334d4889f00d948a493125bfae4512018c9f4731da28","abstract_canon_sha256":"0139ac2afad6f264e4bba14d3e5d50674e587fb28759155014ab4621b371be3a"},"schema_version":"1.0"},"canonical_sha256":"cb22c87632ee1393d07567480735801e4acf5920ba7bf082ac015789a00843ac","source":{"kind":"arxiv","id":"2306.10521","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10521","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10521v2","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10521","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"ZMRMQ5RS5YJZ","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"ZMRMQ5RS5YJZHUDV","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"ZMRMQ5RS","created_at":"2026-07-05T06:43:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZMRMQ5RS5YJZHUDVM5EAONMADZ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.10521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-18T10:59:06Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"46f7552b0ab409d85559334d4889f00d948a493125bfae4512018c9f4731da28","abstract_canon_sha256":"0139ac2afad6f264e4bba14d3e5d50674e587fb28759155014ab4621b371be3a"},"schema_version":"1.0"},"canonical_sha256":"cb22c87632ee1393d07567480735801e4acf5920ba7bf082ac015789a00843ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:03.382145Z","signature_b64":"tgbIyg8l0RG5uP30CZGcCSheJFBFDR12xlymt8ZduntDXzVjoBCbxYKs/DPxMx5i6jotoNivOBUMQcRXOlxlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb22c87632ee1393d07567480735801e4acf5920ba7bf082ac015789a00843ac","last_reissued_at":"2026-07-05T06:43:03.381453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:03.381453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.10521","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gH8X0RpLvTAevUehFDdjWe0gIvJV2E67OlFBi2fZT3Cj2Tc7t73+GvfEh8fbHMcCvGJdJf/qb4X7neHJ46/eCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:49.075919Z"},"content_sha256":"5cbad30480701b0e3e78a585d253f4c566a1c63e9004b5d53535eaaacbd135a8","schema_version":"1.0","event_id":"sha256:5cbad30480701b0e3e78a585d253f4c566a1c63e9004b5d53535eaaacbd135a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZMRMQ5RS5YJZHUDVM5EAONMADZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Lei Xie, Qiao Tian, Yuanzhe Chen, Yuping Wang, Zhichao Wang","submitted_at":"2023-06-18T10:59:06Z","abstract_excerpt":"Language model (LM) based audio generation frameworks, e.g., AudioLM, have recently achieved new state-of-the-art performance in zero-shot audio generation. In this paper, we explore the feasibility of LMs for zero-shot voice conversion. An intuitive approach is to follow AudioLM - Tokenizing speech into semantic and acoustic tokens respectively by HuBERT and SoundStream, and converting source semantic tokens to target acoustic tokens conditioned on acoustic tokens of the target speaker. However, such an approach encounters several issues: 1) the linguistic content contained in semantic tokens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10521","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/2306.10521/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WpHnBRXRvrhLaoYpvWpGWXvYJN4hu9/qRnXqcWf4aHZcytUDwAaFsSkrF0w4y7Mh7upNyCCx3sZGGmLpdJ/DDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:49.076346Z"},"content_sha256":"b913b70c414a9b1d2054db2cfe74198cb241ea7b48f9d55f73a5757f6419abaa","schema_version":"1.0","event_id":"sha256:b913b70c414a9b1d2054db2cfe74198cb241ea7b48f9d55f73a5757f6419abaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ/bundle.json","state_url":"https://pith.science/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T04:12:49Z","links":{"resolver":"https://pith.science/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ","bundle":"https://pith.science/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ/bundle.json","state":"https://pith.science/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMRMQ5RS5YJZHUDVM5EAONMADZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZMRMQ5RS5YJZHUDVM5EAONMADZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0139ac2afad6f264e4bba14d3e5d50674e587fb28759155014ab4621b371be3a","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-18T10:59:06Z","title_canon_sha256":"46f7552b0ab409d85559334d4889f00d948a493125bfae4512018c9f4731da28"},"schema_version":"1.0","source":{"id":"2306.10521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10521","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10521v2","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10521","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"ZMRMQ5RS5YJZ","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"ZMRMQ5RS5YJZHUDV","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"ZMRMQ5RS","created_at":"2026-07-05T06:43:03Z"}],"graph_snapshots":[{"event_id":"sha256:b913b70c414a9b1d2054db2cfe74198cb241ea7b48f9d55f73a5757f6419abaa","target":"graph","created_at":"2026-07-05T06:43:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.10521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model (LM) based audio generation frameworks, e.g., AudioLM, have recently achieved new state-of-the-art performance in zero-shot audio generation. In this paper, we explore the feasibility of LMs for zero-shot voice conversion. An intuitive approach is to follow AudioLM - Tokenizing speech into semantic and acoustic tokens respectively by HuBERT and SoundStream, and converting source semantic tokens to target acoustic tokens conditioned on acoustic tokens of the target speaker. However, such an approach encounters several issues: 1) the linguistic content contained in semantic tokens","authors_text":"Lei Xie, Qiao Tian, Yuanzhe Chen, Yuping Wang, Zhichao Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-18T10:59:06Z","title":"LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10521","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5cbad30480701b0e3e78a585d253f4c566a1c63e9004b5d53535eaaacbd135a8","target":"record","created_at":"2026-07-05T06:43:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0139ac2afad6f264e4bba14d3e5d50674e587fb28759155014ab4621b371be3a","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-18T10:59:06Z","title_canon_sha256":"46f7552b0ab409d85559334d4889f00d948a493125bfae4512018c9f4731da28"},"schema_version":"1.0","source":{"id":"2306.10521","kind":"arxiv","version":2}},"canonical_sha256":"cb22c87632ee1393d07567480735801e4acf5920ba7bf082ac015789a00843ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb22c87632ee1393d07567480735801e4acf5920ba7bf082ac015789a00843ac","first_computed_at":"2026-07-05T06:43:03.381453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:03.381453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tgbIyg8l0RG5uP30CZGcCSheJFBFDR12xlymt8ZduntDXzVjoBCbxYKs/DPxMx5i6jotoNivOBUMQcRXOlxlBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:03.382145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cbad30480701b0e3e78a585d253f4c566a1c63e9004b5d53535eaaacbd135a8","sha256:b913b70c414a9b1d2054db2cfe74198cb241ea7b48f9d55f73a5757f6419abaa"],"state_sha256":"280aece6d9b75d61e5d99ea873e31f23e8f3d5e4012cd31fba70e5d3b566544b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DJJH4jeVYTef7QSpbzpLfTVREFzzUvOFCsg2wwXdtDFA+I1F3y2hH1Q/m9yOPA2BGuS0GEwFK1RJJfBnwxe8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:12:49.078407Z","bundle_sha256":"ae7996b029661fc219169d7699e43f7fa3ebf9966c6e11ca0427cea14d2b64dc"}}