{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UHKJ2V3C5TPI7TITNPZJZPT5ID","short_pith_number":"pith:UHKJ2V3C","schema_version":"1.0","canonical_sha256":"a1d49d5762ecde8fcd136bf29cbe7d40e23ce4ab49d64bda68f8e95d5542ea23","source":{"kind":"arxiv","id":"2401.07333","version":1},"attestation_state":"computed","paper":{"title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Xiaofei Wang, Xie Chen, Yakun Song, Zhuo Chen, Ziyang Ma","submitted_at":"2024-01-14T17:43:55Z","abstract_excerpt":"The language model (LM) approach based on acoustic and linguistic prompts, such as VALL-E, has achieved remarkable progress in the field of zero-shot audio generation. However, existing methods still have some limitations: 1) repetitions, transpositions, and omissions in the output synthesized speech due to limited alignment constraints between audio and phoneme tokens; 2) challenges of fine-grained control over the synthesized speech with autoregressive (AR) language model; 3) infinite silence generation due to the nature of AR-based decoding, especially under the greedy strategy. To alleviat"},"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":"2401.07333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-14T17:43:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"6d1f4195889983820a8d9e1ea2913a54bf1ab1869e75a647dac2b03a55cf9687","abstract_canon_sha256":"aba807873f70155a079878d870f39aa621d05aae0b7117db0fa992de4d24be56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:35.655724Z","signature_b64":"glztxFUwEOcuYyjrKy3uUG9NgmbqLzOD+ADb/7ovKOzk+PM5Z6A9/NEk22r6yRo61ziZIjTI4oqIXUsHapolDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d49d5762ecde8fcd136bf29cbe7d40e23ce4ab49d64bda68f8e95d5542ea23","last_reissued_at":"2026-07-05T07:33:35.655352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:35.655352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Xiaofei Wang, Xie Chen, Yakun Song, Zhuo Chen, Ziyang Ma","submitted_at":"2024-01-14T17:43:55Z","abstract_excerpt":"The language model (LM) approach based on acoustic and linguistic prompts, such as VALL-E, has achieved remarkable progress in the field of zero-shot audio generation. However, existing methods still have some limitations: 1) repetitions, transpositions, and omissions in the output synthesized speech due to limited alignment constraints between audio and phoneme tokens; 2) challenges of fine-grained control over the synthesized speech with autoregressive (AR) language model; 3) infinite silence generation due to the nature of AR-based decoding, especially under the greedy strategy. To alleviat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07333","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/2401.07333/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":"2401.07333","created_at":"2026-07-05T07:33:35.655420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07333v1","created_at":"2026-07-05T07:33:35.655420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07333","created_at":"2026-07-05T07:33:35.655420+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHKJ2V3C5TPI","created_at":"2026-07-05T07:33:35.655420+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHKJ2V3C5TPI7TIT","created_at":"2026-07-05T07:33:35.655420+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHKJ2V3C","created_at":"2026-07-05T07:33:35.655420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10117","citing_title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID","json":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID.json","graph_json":"https://pith.science/api/pith-number/UHKJ2V3C5TPI7TITNPZJZPT5ID/graph.json","events_json":"https://pith.science/api/pith-number/UHKJ2V3C5TPI7TITNPZJZPT5ID/events.json","paper":"https://pith.science/paper/UHKJ2V3C"},"agent_actions":{"view_html":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID","download_json":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID.json","view_paper":"https://pith.science/paper/UHKJ2V3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07333&json=true","fetch_graph":"https://pith.science/api/pith-number/UHKJ2V3C5TPI7TITNPZJZPT5ID/graph.json","fetch_events":"https://pith.science/api/pith-number/UHKJ2V3C5TPI7TITNPZJZPT5ID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID/action/storage_attestation","attest_author":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID/action/author_attestation","sign_citation":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID/action/citation_signature","submit_replication":"https://pith.science/pith/UHKJ2V3C5TPI7TITNPZJZPT5ID/action/replication_record"}},"created_at":"2026-07-05T07:33:35.655420+00:00","updated_at":"2026-07-05T07:33:35.655420+00:00"}