{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ROXLC3ZCZXM6SPC5MS4H5PSIPT","short_pith_number":"pith:ROXLC3ZC","schema_version":"1.0","canonical_sha256":"8baeb16f22cdd9e93c5d64b87ebe487cf424d104c954a6526d5768be31acea05","source":{"kind":"arxiv","id":"2005.08528","version":2},"attestation_state":"computed","paper":{"title":"MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ming Liu, Ming Zhou, Naihan Li, Sheng Zhao, Shujie Liu, Yanqing Liu","submitted_at":"2020-05-18T08:36:12Z","abstract_excerpt":"To speed up the inference of neural speech synthesis, non-autoregressive models receive increasing attention recently. In non-autoregressive models, additional durations of text tokens are required to make a hard alignment between the encoder and the decoder. The duration-based alignment plays a crucial role since it controls the correspondence between text tokens and spectrum frames and determines the rhythm and speed of synthesized audio. To get better duration-based alignment and improve the quality of non-autoregressive speech synthesis, in this paper, we propose a novel neural alignment m"},"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":"2005.08528","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-18T08:36:12Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0b240ccb48da520e40c32c46ed185f1c5617b116d7c545274a8b411848d05a2a","abstract_canon_sha256":"8003a7c978623abc7c37a31b14136270083eb6ab1ab30a1201f6b2cdd3a09cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:06.613048Z","signature_b64":"q45Rz8ML09hgiwbMJVpb4w+hA8XZ2jvfJdXHedjxrEVodYMQ8/21CoqFfm+8k0uhapARatUxHud+bDcneTArBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8baeb16f22cdd9e93c5d64b87ebe487cf424d104c954a6526d5768be31acea05","last_reissued_at":"2026-07-05T01:09:06.612593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:06.612593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ming Liu, Ming Zhou, Naihan Li, Sheng Zhao, Shujie Liu, Yanqing Liu","submitted_at":"2020-05-18T08:36:12Z","abstract_excerpt":"To speed up the inference of neural speech synthesis, non-autoregressive models receive increasing attention recently. In non-autoregressive models, additional durations of text tokens are required to make a hard alignment between the encoder and the decoder. The duration-based alignment plays a crucial role since it controls the correspondence between text tokens and spectrum frames and determines the rhythm and speed of synthesized audio. To get better duration-based alignment and improve the quality of non-autoregressive speech synthesis, in this paper, we propose a novel neural alignment m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08528","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/2005.08528/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":"2005.08528","created_at":"2026-07-05T01:09:06.612648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08528v2","created_at":"2026-07-05T01:09:06.612648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08528","created_at":"2026-07-05T01:09:06.612648+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROXLC3ZCZXM6","created_at":"2026-07-05T01:09:06.612648+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROXLC3ZCZXM6SPC5","created_at":"2026-07-05T01:09:06.612648+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROXLC3ZC","created_at":"2026-07-05T01:09:06.612648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22746","citing_title":"Next Tokens Denoising for Speech Synthesis","ref_index":2019,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT","json":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT.json","graph_json":"https://pith.science/api/pith-number/ROXLC3ZCZXM6SPC5MS4H5PSIPT/graph.json","events_json":"https://pith.science/api/pith-number/ROXLC3ZCZXM6SPC5MS4H5PSIPT/events.json","paper":"https://pith.science/paper/ROXLC3ZC"},"agent_actions":{"view_html":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT","download_json":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT.json","view_paper":"https://pith.science/paper/ROXLC3ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08528&json=true","fetch_graph":"https://pith.science/api/pith-number/ROXLC3ZCZXM6SPC5MS4H5PSIPT/graph.json","fetch_events":"https://pith.science/api/pith-number/ROXLC3ZCZXM6SPC5MS4H5PSIPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT/action/storage_attestation","attest_author":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT/action/author_attestation","sign_citation":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT/action/citation_signature","submit_replication":"https://pith.science/pith/ROXLC3ZCZXM6SPC5MS4H5PSIPT/action/replication_record"}},"created_at":"2026-07-05T01:09:06.612648+00:00","updated_at":"2026-07-05T01:09:06.612648+00:00"}