{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UVJIO3A5UKGLHFR5ISVPLS6ZFG","short_pith_number":"pith:UVJIO3A5","schema_version":"1.0","canonical_sha256":"a552876c1da28cb3963d44aaf5cbd92991ed6155fc2bf114437fb65ca2248881","source":{"kind":"arxiv","id":"1804.02135","version":3},"attestation_state":"computed","paper":{"title":"Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2018-04-06T05:27:14Z","abstract_excerpt":"Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS). However, as they lack the ability to model global characteristics of speech (such as speaker individualities or speaking styles), particularly when these characteristics have not been labeled, making neural autoregressive SS systems more expressive is still an open issue. In this paper, we propose to combine VoiceLoop, an autoregressive SS model, with Variational Autoencoder (VAE). This approach, unlike traditional autoregressive SS systems, uses VAE to model the global characteristics explic"},"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":"1804.02135","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-06T05:27:14Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"27ec8f5015005ee22fcfabe7d50f94468fe2c7aa1ad10a82ed7d2f30a7933cc6","abstract_canon_sha256":"d0e44c96beff0f6e5e05db306953156028bc827643da852863338e9a15634448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:25.176631Z","signature_b64":"duZvI2lf/KMz+G0eu8yxE2eC58XdEj3w//7I8Up9N85siL1bCGYkmcTRYkjvEqxprzP4oU5RX63ADierQilEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a552876c1da28cb3963d44aaf5cbd92991ed6155fc2bf114437fb65ca2248881","last_reissued_at":"2026-05-17T23:54:25.175985Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:25.175985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2018-04-06T05:27:14Z","abstract_excerpt":"Recent advances in neural autoregressive models have improve the performance of speech synthesis (SS). However, as they lack the ability to model global characteristics of speech (such as speaker individualities or speaking styles), particularly when these characteristics have not been labeled, making neural autoregressive SS systems more expressive is still an open issue. In this paper, we propose to combine VoiceLoop, an autoregressive SS model, with Variational Autoencoder (VAE). This approach, unlike traditional autoregressive SS systems, uses VAE to model the global characteristics explic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02135","kind":"arxiv","version":3},"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":"1804.02135","created_at":"2026-05-17T23:54:25.176085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02135v3","created_at":"2026-05-17T23:54:25.176085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02135","created_at":"2026-05-17T23:54:25.176085+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVJIO3A5UKGL","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVJIO3A5UKGLHFR5","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVJIO3A5","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.02479","citing_title":"Fine-grained robust prosody transfer for single-speaker neural text-to-speech","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02784","citing_title":"A Methodology for Controlling the Emotional Expressiveness in Synthetic Speech -- a Deep Learning approach","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG","json":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG.json","graph_json":"https://pith.science/api/pith-number/UVJIO3A5UKGLHFR5ISVPLS6ZFG/graph.json","events_json":"https://pith.science/api/pith-number/UVJIO3A5UKGLHFR5ISVPLS6ZFG/events.json","paper":"https://pith.science/paper/UVJIO3A5"},"agent_actions":{"view_html":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG","download_json":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG.json","view_paper":"https://pith.science/paper/UVJIO3A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02135&json=true","fetch_graph":"https://pith.science/api/pith-number/UVJIO3A5UKGLHFR5ISVPLS6ZFG/graph.json","fetch_events":"https://pith.science/api/pith-number/UVJIO3A5UKGLHFR5ISVPLS6ZFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG/action/storage_attestation","attest_author":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG/action/author_attestation","sign_citation":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG/action/citation_signature","submit_replication":"https://pith.science/pith/UVJIO3A5UKGLHFR5ISVPLS6ZFG/action/replication_record"}},"created_at":"2026-05-17T23:54:25.176085+00:00","updated_at":"2026-05-17T23:54:25.176085+00:00"}