{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DLZOVDMZQUHNBUEVN6LDT2UUF6","short_pith_number":"pith:DLZOVDMZ","schema_version":"1.0","canonical_sha256":"1af2ea8d99850ed0d0956f9639ea942f9f2c7fa2dcac1de47f885955ef53cdfd","source":{"kind":"arxiv","id":"2307.09435","version":1},"attestation_state":"computed","paper":{"title":"SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Yinghao Aaron Li","submitted_at":"2023-07-18T17:09:15Z","abstract_excerpt":"In recent years, large-scale pre-trained speech language models (SLMs) have demonstrated remarkable advancements in various generative speech modeling applications, such as text-to-speech synthesis, voice conversion, and speech enhancement. These applications typically involve mapping text or speech inputs to pre-trained SLM representations, from which target speech is decoded. This paper introduces a new approach, SLMGAN, to leverage SLM representations for discriminative tasks within the generative adversarial network (GAN) framework, specifically for voice conversion. Building upon StarGANv"},"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":"2307.09435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-18T17:09:15Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ce5b8c66e18c952b8048a0d82557345ea8a3deee89d0ce28431c9311e93d87f4","abstract_canon_sha256":"209492a6a43b57c235efa8a423ace955bd91d92837fadd9f31d3e4363a464702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:16.798037Z","signature_b64":"oSiGHAoRGeBFVwRhmdPop6negGLVMgP+GqA1OH9NDFoW98OL4qTZb41kdFspVI+LZROo3+/RGDtGbT1i4J+0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1af2ea8d99850ed0d0956f9639ea942f9f2c7fa2dcac1de47f885955ef53cdfd","last_reissued_at":"2026-07-05T06:32:16.797642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:16.797642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Yinghao Aaron Li","submitted_at":"2023-07-18T17:09:15Z","abstract_excerpt":"In recent years, large-scale pre-trained speech language models (SLMs) have demonstrated remarkable advancements in various generative speech modeling applications, such as text-to-speech synthesis, voice conversion, and speech enhancement. These applications typically involve mapping text or speech inputs to pre-trained SLM representations, from which target speech is decoded. This paper introduces a new approach, SLMGAN, to leverage SLM representations for discriminative tasks within the generative adversarial network (GAN) framework, specifically for voice conversion. Building upon StarGANv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09435","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/2307.09435/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":"2307.09435","created_at":"2026-07-05T06:32:16.797704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.09435v1","created_at":"2026-07-05T06:32:16.797704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09435","created_at":"2026-07-05T06:32:16.797704+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLZOVDMZQUHN","created_at":"2026-07-05T06:32:16.797704+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLZOVDMZQUHNBUEV","created_at":"2026-07-05T06:32:16.797704+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLZOVDMZ","created_at":"2026-07-05T06:32:16.797704+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/DLZOVDMZQUHNBUEVN6LDT2UUF6","json":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6.json","graph_json":"https://pith.science/api/pith-number/DLZOVDMZQUHNBUEVN6LDT2UUF6/graph.json","events_json":"https://pith.science/api/pith-number/DLZOVDMZQUHNBUEVN6LDT2UUF6/events.json","paper":"https://pith.science/paper/DLZOVDMZ"},"agent_actions":{"view_html":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6","download_json":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6.json","view_paper":"https://pith.science/paper/DLZOVDMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.09435&json=true","fetch_graph":"https://pith.science/api/pith-number/DLZOVDMZQUHNBUEVN6LDT2UUF6/graph.json","fetch_events":"https://pith.science/api/pith-number/DLZOVDMZQUHNBUEVN6LDT2UUF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6/action/storage_attestation","attest_author":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6/action/author_attestation","sign_citation":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6/action/citation_signature","submit_replication":"https://pith.science/pith/DLZOVDMZQUHNBUEVN6LDT2UUF6/action/replication_record"}},"created_at":"2026-07-05T06:32:16.797704+00:00","updated_at":"2026-07-05T06:32:16.797704+00:00"}