{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:J3JK6DZLWCOBVJ2KQO4BRS7MM6","short_pith_number":"pith:J3JK6DZL","schema_version":"1.0","canonical_sha256":"4ed2af0f2bb09c1aa74a83b818cbec67abc0a775997e222b21ae31723d030621","source":{"kind":"arxiv","id":"2005.10438","version":2},"attestation_state":"computed","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 "},"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":"2005.10438","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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.10438","created_at":"2026-07-05T01:51:41.681541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10438v2","created_at":"2026-07-05T01:51:41.681541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10438","created_at":"2026-07-05T01:51:41.681541+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3JK6DZLWCOB","created_at":"2026-07-05T01:51:41.681541+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3JK6DZLWCOBVJ2K","created_at":"2026-07-05T01:51:41.681541+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3JK6DZL","created_at":"2026-07-05T01:51:41.681541+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/J3JK6DZLWCOBVJ2KQO4BRS7MM6","json":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6.json","graph_json":"https://pith.science/api/pith-number/J3JK6DZLWCOBVJ2KQO4BRS7MM6/graph.json","events_json":"https://pith.science/api/pith-number/J3JK6DZLWCOBVJ2KQO4BRS7MM6/events.json","paper":"https://pith.science/paper/J3JK6DZL"},"agent_actions":{"view_html":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6","download_json":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6.json","view_paper":"https://pith.science/paper/J3JK6DZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10438&json=true","fetch_graph":"https://pith.science/api/pith-number/J3JK6DZLWCOBVJ2KQO4BRS7MM6/graph.json","fetch_events":"https://pith.science/api/pith-number/J3JK6DZLWCOBVJ2KQO4BRS7MM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/action/storage_attestation","attest_author":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/action/author_attestation","sign_citation":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/action/citation_signature","submit_replication":"https://pith.science/pith/J3JK6DZLWCOBVJ2KQO4BRS7MM6/action/replication_record"}},"created_at":"2026-07-05T01:51:41.681541+00:00","updated_at":"2026-07-05T01:51:41.681541+00:00"}