{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UJCMPK5AEOLOT5A2GBBHF5YZ66","short_pith_number":"pith:UJCMPK5A","canonical_record":{"source":{"id":"2501.09104","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-15T19:42:41Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"bd3d386104497fc0aa810e267c471a8f9726e5346c97731234e44ca25bbe12f5","abstract_canon_sha256":"b05fef7b7ccf5662b59094a89c247b76afcf14687fd55e5095c091a43d45c465"},"schema_version":"1.0"},"canonical_sha256":"a244c7aba02396e9f41a304272f719f7a126762d59bfe27e93390fbe50454738","source":{"kind":"arxiv","id":"2501.09104","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09104","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09104v2","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09104","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"UJCMPK5AEOLO","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"UJCMPK5AEOLOT5A2","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"UJCMPK5A","created_at":"2026-07-05T10:02:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UJCMPK5AEOLOT5A2GBBHF5YZ66","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09104","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-15T19:42:41Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"bd3d386104497fc0aa810e267c471a8f9726e5346c97731234e44ca25bbe12f5","abstract_canon_sha256":"b05fef7b7ccf5662b59094a89c247b76afcf14687fd55e5095c091a43d45c465"},"schema_version":"1.0"},"canonical_sha256":"a244c7aba02396e9f41a304272f719f7a126762d59bfe27e93390fbe50454738","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:58.593901Z","signature_b64":"eHrGFd5GLcU35Q9XYAjC2CNO1WNAs2E91qPDkNpY36+FlyMHkQvZrGsAgzG+2oSaWnmMWdJOmWS79DvdkbM1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a244c7aba02396e9f41a304272f719f7a126762d59bfe27e93390fbe50454738","last_reissued_at":"2026-07-05T10:02:58.593454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:58.593454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09104","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y19czjagC+4b8KhWHgbZD0YRMhaHDTGkAKuaMkx7avSkKCluBzfmKaiK+dTMjzD8mXSGs6RcQlqyfKPomq3OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:05:55.363693Z"},"content_sha256":"e583c9b50d133e0f864804090a35fc3bcefa15f7b29ea4c9bffdbf5fb950340a","schema_version":"1.0","event_id":"sha256:e583c9b50d133e0f864804090a35fc3bcefa15f7b29ea4c9bffdbf5fb950340a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UJCMPK5AEOLOT5A2GBBHF5YZ66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Non-autoregressive Model for Joint STT and TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Brian Kingsbury, Eric Fosler-Lussier, George Saon, Hagai Aronowitz, Luis Lastras, Samuel Thomas, Slava Shechtman, Vishal Sunder","submitted_at":"2025-01-15T19:42:41Z","abstract_excerpt":"In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text modalities as input either individually or together. The proposed model can also be trained with unpaired speech or text data owing to its multimodal nature. We further propose an iterative refinement strategy to improve the STT and TTS performance of our model such that the partial hypothesis at the output can be fed back to the input of our model, thus iteratively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09104","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/2501.09104/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ELT37sUJsrP4Pog3AnWOz+TXNTiuFPeA+ybYNHMgGD4DU9mv59dxxI2kO08CbcFhLeOvl973WRM3NwNL+IK5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:05:55.364255Z"},"content_sha256":"fe278bd1c21f01f5d8410bd03fecee841992a623ca80c462437ea47bee0a2835","schema_version":"1.0","event_id":"sha256:fe278bd1c21f01f5d8410bd03fecee841992a623ca80c462437ea47bee0a2835"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66/bundle.json","state_url":"https://pith.science/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T10:05:55Z","links":{"resolver":"https://pith.science/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66","bundle":"https://pith.science/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66/bundle.json","state":"https://pith.science/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJCMPK5AEOLOT5A2GBBHF5YZ66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UJCMPK5AEOLOT5A2GBBHF5YZ66","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b05fef7b7ccf5662b59094a89c247b76afcf14687fd55e5095c091a43d45c465","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-15T19:42:41Z","title_canon_sha256":"bd3d386104497fc0aa810e267c471a8f9726e5346c97731234e44ca25bbe12f5"},"schema_version":"1.0","source":{"id":"2501.09104","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09104","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09104v2","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09104","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"UJCMPK5AEOLO","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"UJCMPK5AEOLOT5A2","created_at":"2026-07-05T10:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"UJCMPK5A","created_at":"2026-07-05T10:02:58Z"}],"graph_snapshots":[{"event_id":"sha256:fe278bd1c21f01f5d8410bd03fecee841992a623ca80c462437ea47bee0a2835","target":"graph","created_at":"2026-07-05T10:02:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.09104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text modalities as input either individually or together. The proposed model can also be trained with unpaired speech or text data owing to its multimodal nature. We further propose an iterative refinement strategy to improve the STT and TTS performance of our model such that the partial hypothesis at the output can be fed back to the input of our model, thus iteratively","authors_text":"Brian Kingsbury, Eric Fosler-Lussier, George Saon, Hagai Aronowitz, Luis Lastras, Samuel Thomas, Slava Shechtman, Vishal Sunder","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-15T19:42:41Z","title":"A Non-autoregressive Model for Joint STT and TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09104","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e583c9b50d133e0f864804090a35fc3bcefa15f7b29ea4c9bffdbf5fb950340a","target":"record","created_at":"2026-07-05T10:02:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b05fef7b7ccf5662b59094a89c247b76afcf14687fd55e5095c091a43d45c465","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-15T19:42:41Z","title_canon_sha256":"bd3d386104497fc0aa810e267c471a8f9726e5346c97731234e44ca25bbe12f5"},"schema_version":"1.0","source":{"id":"2501.09104","kind":"arxiv","version":2}},"canonical_sha256":"a244c7aba02396e9f41a304272f719f7a126762d59bfe27e93390fbe50454738","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a244c7aba02396e9f41a304272f719f7a126762d59bfe27e93390fbe50454738","first_computed_at":"2026-07-05T10:02:58.593454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:58.593454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eHrGFd5GLcU35Q9XYAjC2CNO1WNAs2E91qPDkNpY36+FlyMHkQvZrGsAgzG+2oSaWnmMWdJOmWS79DvdkbM1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:58.593901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09104","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e583c9b50d133e0f864804090a35fc3bcefa15f7b29ea4c9bffdbf5fb950340a","sha256:fe278bd1c21f01f5d8410bd03fecee841992a623ca80c462437ea47bee0a2835"],"state_sha256":"dff5fa444539b7abea4470e535911da1c0b72503268e8a0e130d7e2b3992a379"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QaVaN/QgHMgl7atlaQel/JZ1ybyskA/JwQb4WcYWfAhs48o+brH4+rJPaDj8jZ+dXNrvzORb7/yUmEdnNXpCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:05:55.373425Z","bundle_sha256":"b3e0f74caae8fdd0fd141e875bc62cc0869267ac9ecfee28cad2a8b769a2e4f4"}}