{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2MN3YJNHD5RIYERJZECW5SSLKH","short_pith_number":"pith:2MN3YJNH","schema_version":"1.0","canonical_sha256":"d31bbc25a71f628c1229c9056eca4b51d6761d10e3d9bb6bd08d6b17c56a7fe3","source":{"kind":"arxiv","id":"1907.08294","version":1},"attestation_state":"computed","paper":{"title":"DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hiroshi Saruwatari, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2019-07-19T09:11:35Z","abstract_excerpt":"This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data. We propose two training algorithms for DNN-based speaker embedding model using an inter-speaker similarity matrix obtained"},"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":"1907.08294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-07-19T09:11:35Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"88defad0115fcd0e06180dbce172971dffc45f4255d816ede2a89a4aa10c54e2","abstract_canon_sha256":"f9d16191bd4e2f5134b7cbc49bc09fb3cded8f4c806232333fd5d62352724d2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:10.308984Z","signature_b64":"SgT6gWwRTo3a1IC6vIw3zxsi3NxKw4w+i1Ga8JweVYtLfy5WOLP/bfcw6ttS93kRYcfpZqyFips2fYmH7M16Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d31bbc25a71f628c1229c9056eca4b51d6761d10e3d9bb6bd08d6b17c56a7fe3","last_reissued_at":"2026-05-17T23:40:10.308432Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:10.308432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hiroshi Saruwatari, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2019-07-19T09:11:35Z","abstract_excerpt":"This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data. We propose two training algorithms for DNN-based speaker embedding model using an inter-speaker similarity matrix obtained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08294","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":"1907.08294","created_at":"2026-05-17T23:40:10.308511+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08294v1","created_at":"2026-05-17T23:40:10.308511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08294","created_at":"2026-05-17T23:40:10.308511+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MN3YJNHD5RI","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MN3YJNHD5RIYERJ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MN3YJNH","created_at":"2026-05-18T12:33:07.085635+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/2MN3YJNHD5RIYERJZECW5SSLKH","json":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH.json","graph_json":"https://pith.science/api/pith-number/2MN3YJNHD5RIYERJZECW5SSLKH/graph.json","events_json":"https://pith.science/api/pith-number/2MN3YJNHD5RIYERJZECW5SSLKH/events.json","paper":"https://pith.science/paper/2MN3YJNH"},"agent_actions":{"view_html":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH","download_json":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH.json","view_paper":"https://pith.science/paper/2MN3YJNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08294&json=true","fetch_graph":"https://pith.science/api/pith-number/2MN3YJNHD5RIYERJZECW5SSLKH/graph.json","fetch_events":"https://pith.science/api/pith-number/2MN3YJNHD5RIYERJZECW5SSLKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH/action/storage_attestation","attest_author":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH/action/author_attestation","sign_citation":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH/action/citation_signature","submit_replication":"https://pith.science/pith/2MN3YJNHD5RIYERJZECW5SSLKH/action/replication_record"}},"created_at":"2026-05-17T23:40:10.308511+00:00","updated_at":"2026-05-17T23:40:10.308511+00:00"}