{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FHZLMCGAGPQN2T2GXK6HJBCAA6","short_pith_number":"pith:FHZLMCGA","schema_version":"1.0","canonical_sha256":"29f2b608c033e0dd4f46babc74844007ad12ac2d11166a769d3e453f9f0278d6","source":{"kind":"arxiv","id":"1704.03626","version":1},"attestation_state":"computed","paper":{"title":"Sampling-based speech parameter generation using moment-matching networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Shinnosuke Takamichi, Tomoki Koriyama","submitted_at":"2017-04-12T05:46:44Z","abstract_excerpt":"This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis produces completely the same speech, i.e., there is no inter-utterance variation in synthetic speech. To give synthetic speech natural inter-utterance variation, this paper builds DNN acoustic models that make it possible to randomly sample speech parameters. The DNNs are trained s"},"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":"1704.03626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-04-12T05:46:44Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1aea8291f437fea178b2631a351b10b3c23f695d09db962afbec310503c798fd","abstract_canon_sha256":"1637313cb65a7607a57ab8762c105445efea4d209ee8c2824a664d2e377e3a89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:27.287591Z","signature_b64":"GcqvS2UuWif+8ESBMYC80YMWkkhZXZP/1eTElnJrH+EIteH4/a+J21s3uPt/++RGuFW1AGIA7q91n7TWr2sNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29f2b608c033e0dd4f46babc74844007ad12ac2d11166a769d3e453f9f0278d6","last_reissued_at":"2026-05-18T00:46:27.286885Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:27.286885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling-based speech parameter generation using moment-matching networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hiroshi Saruwatari, Shinnosuke Takamichi, Tomoki Koriyama","submitted_at":"2017-04-12T05:46:44Z","abstract_excerpt":"This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis produces completely the same speech, i.e., there is no inter-utterance variation in synthetic speech. To give synthetic speech natural inter-utterance variation, this paper builds DNN acoustic models that make it possible to randomly sample speech parameters. The DNNs are trained s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03626","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1704.03626","created_at":"2026-05-18T00:46:27.287006+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.03626v1","created_at":"2026-05-18T00:46:27.287006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03626","created_at":"2026-05-18T00:46:27.287006+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHZLMCGAGPQN","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHZLMCGAGPQN2T2G","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHZLMCGA","created_at":"2026-05-18T12:31:15.632608+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/FHZLMCGAGPQN2T2GXK6HJBCAA6","json":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6.json","graph_json":"https://pith.science/api/pith-number/FHZLMCGAGPQN2T2GXK6HJBCAA6/graph.json","events_json":"https://pith.science/api/pith-number/FHZLMCGAGPQN2T2GXK6HJBCAA6/events.json","paper":"https://pith.science/paper/FHZLMCGA"},"agent_actions":{"view_html":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6","download_json":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6.json","view_paper":"https://pith.science/paper/FHZLMCGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.03626&json=true","fetch_graph":"https://pith.science/api/pith-number/FHZLMCGAGPQN2T2GXK6HJBCAA6/graph.json","fetch_events":"https://pith.science/api/pith-number/FHZLMCGAGPQN2T2GXK6HJBCAA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6/action/storage_attestation","attest_author":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6/action/author_attestation","sign_citation":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6/action/citation_signature","submit_replication":"https://pith.science/pith/FHZLMCGAGPQN2T2GXK6HJBCAA6/action/replication_record"}},"created_at":"2026-05-18T00:46:27.287006+00:00","updated_at":"2026-05-18T00:46:27.287006+00:00"}