{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SBTLLN7VSFUYV7BP2PIHRVLVXX","short_pith_number":"pith:SBTLLN7V","schema_version":"1.0","canonical_sha256":"9066b5b7f591698afc2fd3d078d575bdc7e3b0be2a3b1ded48a02d3babb94395","source":{"kind":"arxiv","id":"2408.11842","version":2},"attestation_state":"computed","paper":{"title":"Non-Causal to Causal SSL-Supported Transfer Learning: Towards a High-Performance Low-Latency Speech Vocoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andreas B\\\"ar, Marvin Sach, Renzheng Shi, Tim Fingscheidt, Wouter Tirry","submitted_at":"2024-08-07T12:49:40Z","abstract_excerpt":"Recently, BigVGAN has emerged as high-performance speech vocoder. Its sequence-to-sequence-based synthesis, however, prohibits usage in low-latency conversational applications. Our work addresses this shortcoming in three steps. First, we introduce low latency into BigVGAN via implementing causal convolutions, yielding decreased performance. Second, to regain performance, we propose a teacher-student transfer learning scheme to distill the high-delay non-causal BigVGAN into our low-latency causal vocoder. Third, taking advantage of a self-supervised learning (SSL) model, in our case wav2vec 2."},"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":"2408.11842","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-07T12:49:40Z","cross_cats_sorted":[],"title_canon_sha256":"8d1e0bddeebd9a6203a6ae067a957dcebd08fc17ae018aeed95487ca11def20f","abstract_canon_sha256":"cfdfe3c427329bd5530cc388d4750b40526a71b9317848f1919dfbc315ed4a19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:12.224798Z","signature_b64":"nrRk7ZpVOEdDyWpsB6mSV2liGuwd8Jzw/cw2HZPDU0jhSiEIXAoVU6dbe1HEPDM8JwIHeLUkE7FTGo4k9D3qBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9066b5b7f591698afc2fd3d078d575bdc7e3b0be2a3b1ded48a02d3babb94395","last_reissued_at":"2026-07-05T08:59:12.224322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:12.224322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Causal to Causal SSL-Supported Transfer Learning: Towards a High-Performance Low-Latency Speech Vocoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andreas B\\\"ar, Marvin Sach, Renzheng Shi, Tim Fingscheidt, Wouter Tirry","submitted_at":"2024-08-07T12:49:40Z","abstract_excerpt":"Recently, BigVGAN has emerged as high-performance speech vocoder. Its sequence-to-sequence-based synthesis, however, prohibits usage in low-latency conversational applications. Our work addresses this shortcoming in three steps. First, we introduce low latency into BigVGAN via implementing causal convolutions, yielding decreased performance. Second, to regain performance, we propose a teacher-student transfer learning scheme to distill the high-delay non-causal BigVGAN into our low-latency causal vocoder. Third, taking advantage of a self-supervised learning (SSL) model, in our case wav2vec 2."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11842","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/2408.11842/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":"2408.11842","created_at":"2026-07-05T08:59:12.224383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11842v2","created_at":"2026-07-05T08:59:12.224383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11842","created_at":"2026-07-05T08:59:12.224383+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBTLLN7VSFUY","created_at":"2026-07-05T08:59:12.224383+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBTLLN7VSFUYV7BP","created_at":"2026-07-05T08:59:12.224383+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBTLLN7V","created_at":"2026-07-05T08:59:12.224383+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/SBTLLN7VSFUYV7BP2PIHRVLVXX","json":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX.json","graph_json":"https://pith.science/api/pith-number/SBTLLN7VSFUYV7BP2PIHRVLVXX/graph.json","events_json":"https://pith.science/api/pith-number/SBTLLN7VSFUYV7BP2PIHRVLVXX/events.json","paper":"https://pith.science/paper/SBTLLN7V"},"agent_actions":{"view_html":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX","download_json":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX.json","view_paper":"https://pith.science/paper/SBTLLN7V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11842&json=true","fetch_graph":"https://pith.science/api/pith-number/SBTLLN7VSFUYV7BP2PIHRVLVXX/graph.json","fetch_events":"https://pith.science/api/pith-number/SBTLLN7VSFUYV7BP2PIHRVLVXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX/action/storage_attestation","attest_author":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX/action/author_attestation","sign_citation":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX/action/citation_signature","submit_replication":"https://pith.science/pith/SBTLLN7VSFUYV7BP2PIHRVLVXX/action/replication_record"}},"created_at":"2026-07-05T08:59:12.224383+00:00","updated_at":"2026-07-05T08:59:12.224383+00:00"}