{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4POGXGDORQ6BF6WAMS2TCYXZ3T","short_pith_number":"pith:4POGXGDO","schema_version":"1.0","canonical_sha256":"e3dc6b986e8c3c12fac064b53162f9dcfc41b3aecf89a308433c40a8b8feb9cd","source":{"kind":"arxiv","id":"2210.09916","version":1},"attestation_state":"computed","paper":{"title":"Mid-attribute speaker generation using optimal-transport-based interpolation of Gaussian mixture models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aya Watanabe, Detai Xin, Hiroshi Saruwatari, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2022-10-18T14:59:25Z","abstract_excerpt":"In this paper, we propose a method for intermediating multiple speakers' attributes and diversifying their voice characteristics in ``speaker generation,'' an emerging task that aims to synthesize a nonexistent speaker's naturally sounding voice. The conventional TacoSpawn-based speaker generation method represents the distributions of speaker embeddings by Gaussian mixture models (GMMs) conditioned with speaker attributes. Although this method enables the sampling of various speakers from the speaker-attribute-aware GMMs, it is not yet clear whether the learned distributions can represent spe"},"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":"2210.09916","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-18T14:59:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"137325a84500a30902bd8748f39bc571e8087d48b1566b6fc7a35068751e532c","abstract_canon_sha256":"0d8030a5541f3b2f16a77e19696dc3855a4fec4b8277d7255df5ea69529544b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:00.765116Z","signature_b64":"V8y2om5StJvslLTi0C+JmKc0/sLl/iSCKPImIDVKk9Cy0EXrykV52tXjFuK6UNB3uUUU5pAVgacEAQ8+t2UfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3dc6b986e8c3c12fac064b53162f9dcfc41b3aecf89a308433c40a8b8feb9cd","last_reissued_at":"2026-07-05T05:08:00.764644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:00.764644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mid-attribute speaker generation using optimal-transport-based interpolation of Gaussian mixture models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aya Watanabe, Detai Xin, Hiroshi Saruwatari, Shinnosuke Takamichi, Yuki Saito","submitted_at":"2022-10-18T14:59:25Z","abstract_excerpt":"In this paper, we propose a method for intermediating multiple speakers' attributes and diversifying their voice characteristics in ``speaker generation,'' an emerging task that aims to synthesize a nonexistent speaker's naturally sounding voice. The conventional TacoSpawn-based speaker generation method represents the distributions of speaker embeddings by Gaussian mixture models (GMMs) conditioned with speaker attributes. Although this method enables the sampling of various speakers from the speaker-attribute-aware GMMs, it is not yet clear whether the learned distributions can represent spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09916","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.09916/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":"2210.09916","created_at":"2026-07-05T05:08:00.764702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09916v1","created_at":"2026-07-05T05:08:00.764702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09916","created_at":"2026-07-05T05:08:00.764702+00:00"},{"alias_kind":"pith_short_12","alias_value":"4POGXGDORQ6B","created_at":"2026-07-05T05:08:00.764702+00:00"},{"alias_kind":"pith_short_16","alias_value":"4POGXGDORQ6BF6WA","created_at":"2026-07-05T05:08:00.764702+00:00"},{"alias_kind":"pith_short_8","alias_value":"4POGXGDO","created_at":"2026-07-05T05:08:00.764702+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/4POGXGDORQ6BF6WAMS2TCYXZ3T","json":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T.json","graph_json":"https://pith.science/api/pith-number/4POGXGDORQ6BF6WAMS2TCYXZ3T/graph.json","events_json":"https://pith.science/api/pith-number/4POGXGDORQ6BF6WAMS2TCYXZ3T/events.json","paper":"https://pith.science/paper/4POGXGDO"},"agent_actions":{"view_html":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T","download_json":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T.json","view_paper":"https://pith.science/paper/4POGXGDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09916&json=true","fetch_graph":"https://pith.science/api/pith-number/4POGXGDORQ6BF6WAMS2TCYXZ3T/graph.json","fetch_events":"https://pith.science/api/pith-number/4POGXGDORQ6BF6WAMS2TCYXZ3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T/action/storage_attestation","attest_author":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T/action/author_attestation","sign_citation":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T/action/citation_signature","submit_replication":"https://pith.science/pith/4POGXGDORQ6BF6WAMS2TCYXZ3T/action/replication_record"}},"created_at":"2026-07-05T05:08:00.764702+00:00","updated_at":"2026-07-05T05:08:00.764702+00:00"}