{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DFKIMJUFWRUZ6RIMRZSRRJGQ4D","short_pith_number":"pith:DFKIMJUF","schema_version":"1.0","canonical_sha256":"1954862685b4699f450c8e6518a4d0e0cf146ada74b124d3aa8e18c03f3c4eaf","source":{"kind":"arxiv","id":"2110.12539","version":3},"attestation_state":"computed","paper":{"title":"Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Antonio Bonafonte, Jonas Rohnke, Marek Strong, Mateusz {\\L}ajszczak, Trevor Wood","submitted_at":"2021-10-24T22:15:01Z","abstract_excerpt":"We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variational Autoencoder (VQ-VAE) architectures. Compared to these previous architectures, our proposed model retains the benefits of using an utterance-level bottleneck, while keeping significant representation power and a discretized latent space small enough for efficient prediction from text. We train the model on recordings in the expressive task-oriented dialogues domain and show t"},"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":"2110.12539","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-24T22:15:01Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"125fb3578dd59226fdc2079ee4a82f48b272a7ce6fe95e4fb9a63b6316c22ae9","abstract_canon_sha256":"3f07375411444d246e3ecbed2225b0a9666caf979db2768cccb85a720dcd2ef8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:36.301519Z","signature_b64":"4Pzqway/cqYeFl/7Ec8vgZ4rA0XNB35ACio2ghPdCtYVdyuQ+D5u8lMoL9faqF6MzAK/sMXEwkYppqQK6eqRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1954862685b4699f450c8e6518a4d0e0cf146ada74b124d3aa8e18c03f3c4eaf","last_reissued_at":"2026-07-05T06:50:36.301026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:36.301026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Antonio Bonafonte, Jonas Rohnke, Marek Strong, Mateusz {\\L}ajszczak, Trevor Wood","submitted_at":"2021-10-24T22:15:01Z","abstract_excerpt":"We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variational Autoencoder (VQ-VAE) architectures. Compared to these previous architectures, our proposed model retains the benefits of using an utterance-level bottleneck, while keeping significant representation power and a discretized latent space small enough for efficient prediction from text. We train the model on recordings in the expressive task-oriented dialogues domain and show t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12539","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.12539/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":"2110.12539","created_at":"2026-07-05T06:50:36.301086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12539v3","created_at":"2026-07-05T06:50:36.301086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12539","created_at":"2026-07-05T06:50:36.301086+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFKIMJUFWRUZ","created_at":"2026-07-05T06:50:36.301086+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFKIMJUFWRUZ6RIM","created_at":"2026-07-05T06:50:36.301086+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFKIMJUF","created_at":"2026-07-05T06:50:36.301086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01101","citing_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D","json":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D.json","graph_json":"https://pith.science/api/pith-number/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/graph.json","events_json":"https://pith.science/api/pith-number/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/events.json","paper":"https://pith.science/paper/DFKIMJUF"},"agent_actions":{"view_html":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D","download_json":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D.json","view_paper":"https://pith.science/paper/DFKIMJUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12539&json=true","fetch_graph":"https://pith.science/api/pith-number/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/graph.json","fetch_events":"https://pith.science/api/pith-number/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/action/storage_attestation","attest_author":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/action/author_attestation","sign_citation":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/action/citation_signature","submit_replication":"https://pith.science/pith/DFKIMJUFWRUZ6RIMRZSRRJGQ4D/action/replication_record"}},"created_at":"2026-07-05T06:50:36.301086+00:00","updated_at":"2026-07-05T06:50:36.301086+00:00"}