{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3HY4XLMF2WJJBHTSCZME32W4MP","short_pith_number":"pith:3HY4XLMF","schema_version":"1.0","canonical_sha256":"d9f1cbad85d592909e7216584deadc63d24f814811126a141d511972cf81766a","source":{"kind":"arxiv","id":"2204.11806","version":3},"attestation_state":"computed","paper":{"title":"Parallel Synthesis for Autoregressive Speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andy T. Liu, Da-Rong Liu, Hung-yi Lee, Po-chun Hsu","submitted_at":"2022-04-25T17:33:22Z","abstract_excerpt":"Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time steps. Though it synthesizes natural human speech, the iterative generation inevitably makes the synthesis time proportional to the utterance length, leading to low efficiency. Many works were dedicated to generating the whole speech sequence in parallel and proposed GAN-based, flow-based, and score-based vocoders. This paper proposed a new thought for the a"},"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":"2204.11806","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-25T17:33:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"65c2160c8326ad0c9534cbed6d81eb08b49d33a91321fb779841f1db1e4e07f3","abstract_canon_sha256":"c7ef10a8c2146cdfad10297a212553b661e8676c52733628a656b78512a1348d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:39.233611Z","signature_b64":"5oXWZsQIxmyIiPJMVeMj4rQ03afN7GCoA6sScQASZ+UiRzq5GhzhgO8cGU3OkTubI7CC/M9KE8a6qAQu3WJZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f1cbad85d592909e7216584deadc63d24f814811126a141d511972cf81766a","last_reissued_at":"2026-07-05T08:27:39.233170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:39.233170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Synthesis for Autoregressive Speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andy T. Liu, Da-Rong Liu, Hung-yi Lee, Po-chun Hsu","submitted_at":"2022-04-25T17:33:22Z","abstract_excerpt":"Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time steps. Though it synthesizes natural human speech, the iterative generation inevitably makes the synthesis time proportional to the utterance length, leading to low efficiency. Many works were dedicated to generating the whole speech sequence in parallel and proposed GAN-based, flow-based, and score-based vocoders. This paper proposed a new thought for the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11806","kind":"arxiv","version":3},"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/2204.11806/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":"2204.11806","created_at":"2026-07-05T08:27:39.233234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11806v3","created_at":"2026-07-05T08:27:39.233234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11806","created_at":"2026-07-05T08:27:39.233234+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HY4XLMF2WJJ","created_at":"2026-07-05T08:27:39.233234+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HY4XLMF2WJJBHTS","created_at":"2026-07-05T08:27:39.233234+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HY4XLMF","created_at":"2026-07-05T08:27:39.233234+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/3HY4XLMF2WJJBHTSCZME32W4MP","json":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP.json","graph_json":"https://pith.science/api/pith-number/3HY4XLMF2WJJBHTSCZME32W4MP/graph.json","events_json":"https://pith.science/api/pith-number/3HY4XLMF2WJJBHTSCZME32W4MP/events.json","paper":"https://pith.science/paper/3HY4XLMF"},"agent_actions":{"view_html":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP","download_json":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP.json","view_paper":"https://pith.science/paper/3HY4XLMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11806&json=true","fetch_graph":"https://pith.science/api/pith-number/3HY4XLMF2WJJBHTSCZME32W4MP/graph.json","fetch_events":"https://pith.science/api/pith-number/3HY4XLMF2WJJBHTSCZME32W4MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP/action/storage_attestation","attest_author":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP/action/author_attestation","sign_citation":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP/action/citation_signature","submit_replication":"https://pith.science/pith/3HY4XLMF2WJJBHTSCZME32W4MP/action/replication_record"}},"created_at":"2026-07-05T08:27:39.233234+00:00","updated_at":"2026-07-05T08:27:39.233234+00:00"}