{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TV7BUSLEZQW5FKCHECRSS5Z3YJ","short_pith_number":"pith:TV7BUSLE","schema_version":"1.0","canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","source":{"kind":"arxiv","id":"2305.16107","version":1},"attestation_state":"computed","paper":{"title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jinyu Li, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yu Wu, Zhuo Chen, Ziqiang Zhang","submitted_at":"2023-05-25T14:39:47Z","abstract_excerpt":"Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text, such as speech-to-text, text-to-text, text-to-speech, and speech-to-speech tasks, as a conditional codec language model task via multi-task learning framework. To accomplish this, we first convert all the speech utterances to discrete tokens (similar to the textual data) using an offline n"},"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":"2305.16107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T14:39:47Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b8b6ff34d24950cb06dc7bb67b4d8a7b8380eae6b45f884670fc934162f78fda","abstract_canon_sha256":"25886727934d9d421ce5af623934acd0ff28770912b0bbf982f5b981f9383d20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:59.666557Z","signature_b64":"lRsdbP6eMWkmk60W11oHsnyLxqzZFnKB6T0L+5E7nCYs2WRlK16VzItuD885Q1Lvn5asKOsCOEOvVMFmCnSzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d7e1a4964cc2dd2a84720a329773bc240e0569de5500e9fa8eb3d414f4d038a","last_reissued_at":"2026-07-05T06:13:59.666165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:59.666165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jinyu Li, Long Zhou, Shujie Liu, Tianrui Wang, Yashesh Gaur, Yu Wu, Zhuo Chen, Ziqiang Zhang","submitted_at":"2023-05-25T14:39:47Z","abstract_excerpt":"Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text, such as speech-to-text, text-to-text, text-to-speech, and speech-to-speech tasks, as a conditional codec language model task via multi-task learning framework. To accomplish this, we first convert all the speech utterances to discrete tokens (similar to the textual data) using an offline n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16107","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/2305.16107/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":"2305.16107","created_at":"2026-07-05T06:13:59.666220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16107v1","created_at":"2026-07-05T06:13:59.666220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16107","created_at":"2026-07-05T06:13:59.666220+00:00"},{"alias_kind":"pith_short_12","alias_value":"TV7BUSLEZQW5","created_at":"2026-07-05T06:13:59.666220+00:00"},{"alias_kind":"pith_short_16","alias_value":"TV7BUSLEZQW5FKCH","created_at":"2026-07-05T06:13:59.666220+00:00"},{"alias_kind":"pith_short_8","alias_value":"TV7BUSLE","created_at":"2026-07-05T06:13:59.666220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":237,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14294","citing_title":"DASB - Discrete Audio and Speech Benchmark","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2411.17690","citing_title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06582","citing_title":"PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ","json":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ.json","graph_json":"https://pith.science/api/pith-number/TV7BUSLEZQW5FKCHECRSS5Z3YJ/graph.json","events_json":"https://pith.science/api/pith-number/TV7BUSLEZQW5FKCHECRSS5Z3YJ/events.json","paper":"https://pith.science/paper/TV7BUSLE"},"agent_actions":{"view_html":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ","download_json":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ.json","view_paper":"https://pith.science/paper/TV7BUSLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16107&json=true","fetch_graph":"https://pith.science/api/pith-number/TV7BUSLEZQW5FKCHECRSS5Z3YJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TV7BUSLEZQW5FKCHECRSS5Z3YJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/action/storage_attestation","attest_author":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/action/author_attestation","sign_citation":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/action/citation_signature","submit_replication":"https://pith.science/pith/TV7BUSLEZQW5FKCHECRSS5Z3YJ/action/replication_record"}},"created_at":"2026-07-05T06:13:59.666220+00:00","updated_at":"2026-07-05T06:13:59.666220+00:00"}