{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:J3JK6DZLWCOBVJ2KQO4BRS7MM6","short_pith_number":"pith:J3JK6DZL","canonical_record":{"source":{"id":"2005.10438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-21T02:52:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"90e88c717e86d83ca3aedb47ff763ad234f2ba4eceb2860699bf96f94c8c8d85","abstract_canon_sha256":"15ad4951e991756e8c570990b9678fe43af79a888608f7f842489a303e29f599"},"schema_version":"1.0"},"canonical_sha256":"4ed2af0f2bb09c1aa74a83b818cbec67abc0a775997e222b21ae31723d030621","source":{"kind":"arxiv","id":"2005.10438","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10438","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10438v2","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10438","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"J3JK6DZLWCOB","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"J3JK6DZLWCOBVJ2K","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"J3JK6DZL","created_at":"2026-07-05T01:51:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:J3JK6DZLWCOBVJ2KQO4BRS7MM6","target":"record","payload":{"canonical_record":{"source":{"id":"2005.10438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-21T02:52:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"90e88c717e86d83ca3aedb47ff763ad234f2ba4eceb2860699bf96f94c8c8d85","abstract_canon_sha256":"15ad4951e991756e8c570990b9678fe43af79a888608f7f842489a303e29f599"},"schema_version":"1.0"},"canonical_sha256":"4ed2af0f2bb09c1aa74a83b818cbec67abc0a775997e222b21ae31723d030621","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:41.681926Z","signature_b64":"g55Q3u6MepxsFdaVG/KcTO/P0SzDRY98GClfYoW5fzh68vjUzWwVjERVCiN9E0vbxvuZ+D/cwxwq4/kik0gRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed2af0f2bb09c1aa74a83b818cbec67abc0a775997e222b21ae31723d030621","last_reissued_at":"2026-07-05T01:51:41.681483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:41.681483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.10438","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":"2026-07-05T01:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNDHVzKjprNH87kxXIpQTWm9br0bYSFUOuBhoeFUZ2i14Y0ZxqXMVtzcFxgHLlBTsM9g6o6eaum/b9oR8tXiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:07:36.181468Z"},"content_sha256":"5df73683295ec102c6982b9a8831ed873265c5689552c556eec22b7ce1bc11ed","schema_version":"1.0","event_id":"sha256:5df73683295ec102c6982b9a8831ed873265c5689552c556eec22b7ce1bc11ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:J3JK6DZLWCOBVJ2KQO4BRS7MM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conversational End-to-End TTS for Voice Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Frank K. Soong, Haohan Guo, Lei He, Lei Xie, Shaofei Zhang","submitted_at":"2020-05-21T02:52:25Z","abstract_excerpt":"End-to-end neural TTS has achieved superior performance on reading style speech synthesis. However, it's still a challenge to build a high-quality conversational TTS due to the limitations of the corpus and modeling capability. This study aims at building a conversational TTS for a voice agent under sequence to sequence modeling framework. We firstly construct a spontaneous conversational speech corpus well designed for the voice agent with a new recording scheme ensuring both recording quality and conversational speaking style. Secondly, we propose a conversation context-aware end-to-end TTS "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10438","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/2005.10438/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":"2026-07-05T01:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aARuS81Ift+SLbJBn6u4W5vZeInw+UMSqIcMhtygHzAkU2J/6E23mFifbLu9svkmt/RmDAarHeqIaILcKYuyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:07:36.181997Z"},"content_sha256":"543763790edef8ea9cc76af8c3f5f17c0b93a3f411f50bdcffe4259d8c1b3e2b","schema_version":"1.0","event_id":"sha256:543763790edef8ea9cc76af8c3f5f17c0b93a3f411f50bdcffe4259d8c1b3e2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/bundle.json","state_url":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/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":"2026-08-19T03:07:36Z","links":{"resolver":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6","bundle":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/bundle.json","state":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:J3JK6DZLWCOBVJ2KQO4BRS7MM6","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":"15ad4951e991756e8c570990b9678fe43af79a888608f7f842489a303e29f599","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-21T02:52:25Z","title_canon_sha256":"90e88c717e86d83ca3aedb47ff763ad234f2ba4eceb2860699bf96f94c8c8d85"},"schema_version":"1.0","source":{"id":"2005.10438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10438","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10438v2","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10438","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"J3JK6DZLWCOB","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"J3JK6DZLWCOBVJ2K","created_at":"2026-07-05T01:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"J3JK6DZL","created_at":"2026-07-05T01:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:543763790edef8ea9cc76af8c3f5f17c0b93a3f411f50bdcffe4259d8c1b3e2b","target":"graph","created_at":"2026-07-05T01:51:41Z","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/2005.10438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end neural TTS has achieved superior performance on reading style speech synthesis. However, it's still a challenge to build a high-quality conversational TTS due to the limitations of the corpus and modeling capability. This study aims at building a conversational TTS for a voice agent under sequence to sequence modeling framework. We firstly construct a spontaneous conversational speech corpus well designed for the voice agent with a new recording scheme ensuring both recording quality and conversational speaking style. Secondly, we propose a conversation context-aware end-to-end TTS ","authors_text":"Frank K. Soong, Haohan Guo, Lei He, Lei Xie, Shaofei Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-21T02:52:25Z","title":"Conversational End-to-End TTS for Voice Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10438","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":"sha256:5df73683295ec102c6982b9a8831ed873265c5689552c556eec22b7ce1bc11ed","target":"record","created_at":"2026-07-05T01:51:41Z","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":"15ad4951e991756e8c570990b9678fe43af79a888608f7f842489a303e29f599","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-21T02:52:25Z","title_canon_sha256":"90e88c717e86d83ca3aedb47ff763ad234f2ba4eceb2860699bf96f94c8c8d85"},"schema_version":"1.0","source":{"id":"2005.10438","kind":"arxiv","version":2}},"canonical_sha256":"4ed2af0f2bb09c1aa74a83b818cbec67abc0a775997e222b21ae31723d030621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ed2af0f2bb09c1aa74a83b818cbec67abc0a775997e222b21ae31723d030621","first_computed_at":"2026-07-05T01:51:41.681483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:41.681483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g55Q3u6MepxsFdaVG/KcTO/P0SzDRY98GClfYoW5fzh68vjUzWwVjERVCiN9E0vbxvuZ+D/cwxwq4/kik0gRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:41.681926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.10438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5df73683295ec102c6982b9a8831ed873265c5689552c556eec22b7ce1bc11ed","sha256:543763790edef8ea9cc76af8c3f5f17c0b93a3f411f50bdcffe4259d8c1b3e2b"],"state_sha256":"08abbced0aac7df75845d5f76d2e240fd1fd571ad9a7220bff877d3fcda2ec81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtjytdWw9+QI3AFxbsAtBT0OSCfNXFSxvpCm+WgL9sNnC1l/gjOQGlxoYdNNdcs9Hj3WgyJ1C5eO5On5LTsbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:07:36.185933Z","bundle_sha256":"38efcd72f7063e76a6db4794ae1e804fe8e82659cb7a54a17766fb8baea7ddf6"}}