{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KKSOR4LG6RDHXXEROFB7NS5TM7","short_pith_number":"pith:KKSOR4LG","schema_version":"1.0","canonical_sha256":"52a4e8f166f4467bdc917143f6cbb367dce5b36f6c5f0b778ea2f99be67d3d58","source":{"kind":"arxiv","id":"1705.08947","version":2},"attestation_state":"computed","paper":{"title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Gibiansky, Gregory Diamos, John Miller, Jonathan Raiman, Kainan Peng, Sercan Arik, Wei Ping, Yanqi Zhou","submitted_at":"2017-05-24T19:53:13Z","abstract_excerpt":"We introduce a technique for augmenting neural text-to-speech (TTS) with lowdimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-ofthe-art approaches for single-speaker neural TTS: Deep Voice 1 and Tacotron. We introduce Deep Voice 2, which is based on a similar pipeline with Deep Voice 1, but constructed with higher performance building blocks and demonstrates a significant audio quality improvement over Deep Voice 1. We improve Tacotron by introducing a post-processing neural vocoder, and demon"},"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":"1705.08947","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-24T19:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"ea27f32f9740fd86db1bf7faaf7758959269b83f609be1ea5f03c34bbe80d8a3","abstract_canon_sha256":"2f220bc63e2b1c6ba7b2d0ceee7d672ad3378ba8c7a55ba5221bdd02a56bd89a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:37.130555Z","signature_b64":"qGIKwSffAGc95e63E4lzIrpHLVSbGKttI4uY1o3siRM9AKFqFNkZgztRPzhb6666VZWxJ9Ny8CNxeCtWzvNhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52a4e8f166f4467bdc917143f6cbb367dce5b36f6c5f0b778ea2f99be67d3d58","last_reissued_at":"2026-05-18T00:34:37.129873Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:37.129873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Gibiansky, Gregory Diamos, John Miller, Jonathan Raiman, Kainan Peng, Sercan Arik, Wei Ping, Yanqi Zhou","submitted_at":"2017-05-24T19:53:13Z","abstract_excerpt":"We introduce a technique for augmenting neural text-to-speech (TTS) with lowdimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-ofthe-art approaches for single-speaker neural TTS: Deep Voice 1 and Tacotron. We introduce Deep Voice 2, which is based on a similar pipeline with Deep Voice 1, but constructed with higher performance building blocks and demonstrates a significant audio quality improvement over Deep Voice 1. We improve Tacotron by introducing a post-processing neural vocoder, and demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08947","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":""},"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":"1705.08947","created_at":"2026-05-18T00:34:37.129967+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.08947v2","created_at":"2026-05-18T00:34:37.129967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08947","created_at":"2026-05-18T00:34:37.129967+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKSOR4LG6RDH","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKSOR4LG6RDHXXER","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKSOR4LG","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.01749","citing_title":"Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09006","citing_title":"Forward-Backward Decoding for Regularizing End-to-End TTS","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7","json":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7.json","graph_json":"https://pith.science/api/pith-number/KKSOR4LG6RDHXXEROFB7NS5TM7/graph.json","events_json":"https://pith.science/api/pith-number/KKSOR4LG6RDHXXEROFB7NS5TM7/events.json","paper":"https://pith.science/paper/KKSOR4LG"},"agent_actions":{"view_html":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7","download_json":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7.json","view_paper":"https://pith.science/paper/KKSOR4LG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.08947&json=true","fetch_graph":"https://pith.science/api/pith-number/KKSOR4LG6RDHXXEROFB7NS5TM7/graph.json","fetch_events":"https://pith.science/api/pith-number/KKSOR4LG6RDHXXEROFB7NS5TM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7/action/storage_attestation","attest_author":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7/action/author_attestation","sign_citation":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7/action/citation_signature","submit_replication":"https://pith.science/pith/KKSOR4LG6RDHXXEROFB7NS5TM7/action/replication_record"}},"created_at":"2026-05-18T00:34:37.129967+00:00","updated_at":"2026-05-18T00:34:37.129967+00:00"}