{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WARRYYBEVSAMQFT2FNTWNWJBPI","short_pith_number":"pith:WARRYYBE","schema_version":"1.0","canonical_sha256":"b0231c6024ac80c8167a2b6766d9217a3184500134bdec1e62f032061093d172","source":{"kind":"arxiv","id":"2106.15123","version":1},"attestation_state":"computed","paper":{"title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Hanbin Bae, Hoon-Young Cho, Jae-Sung Bae, Taejun Bak, Young-Ik Kim","submitted_at":"2021-06-29T07:06:42Z","abstract_excerpt":"Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large pitch-shift scale suffers from audio quality degradation, and speaker characteristics deformation. To address this problem, we propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. This model, called FastPitchFormant, has a unique structure that handles text and acoustic features in parallel. With modeling each fe"},"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":"2106.15123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T07:06:42Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP"],"title_canon_sha256":"2d057be2941d547dac4abb02538904e07d64a6f867d352c7804c633b6951fe62","abstract_canon_sha256":"55ecd54d69cdc000ea03d5f46394f131148811666f287ac4996c11a614a14b11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:05.510074Z","signature_b64":"4iu1b5qfRLiB3BSIKXUHyrrULJzYcy4XX5lMZB5ZqWU+g1W78Ed/D36qXh3Zjlyp9VWrSPvVkuEV9tEo/8LQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0231c6024ac80c8167a2b6766d9217a3184500134bdec1e62f032061093d172","last_reissued_at":"2026-07-05T02:53:05.509558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:05.509558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Hanbin Bae, Hoon-Young Cho, Jae-Sung Bae, Taejun Bak, Young-Ik Kim","submitted_at":"2021-06-29T07:06:42Z","abstract_excerpt":"Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large pitch-shift scale suffers from audio quality degradation, and speaker characteristics deformation. To address this problem, we propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. This model, called FastPitchFormant, has a unique structure that handles text and acoustic features in parallel. With modeling each fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15123","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/2106.15123/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":"2106.15123","created_at":"2026-07-05T02:53:05.509613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15123v1","created_at":"2026-07-05T02:53:05.509613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15123","created_at":"2026-07-05T02:53:05.509613+00:00"},{"alias_kind":"pith_short_12","alias_value":"WARRYYBEVSAM","created_at":"2026-07-05T02:53:05.509613+00:00"},{"alias_kind":"pith_short_16","alias_value":"WARRYYBEVSAMQFT2","created_at":"2026-07-05T02:53:05.509613+00:00"},{"alias_kind":"pith_short_8","alias_value":"WARRYYBE","created_at":"2026-07-05T02:53:05.509613+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/WARRYYBEVSAMQFT2FNTWNWJBPI","json":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI.json","graph_json":"https://pith.science/api/pith-number/WARRYYBEVSAMQFT2FNTWNWJBPI/graph.json","events_json":"https://pith.science/api/pith-number/WARRYYBEVSAMQFT2FNTWNWJBPI/events.json","paper":"https://pith.science/paper/WARRYYBE"},"agent_actions":{"view_html":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI","download_json":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI.json","view_paper":"https://pith.science/paper/WARRYYBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15123&json=true","fetch_graph":"https://pith.science/api/pith-number/WARRYYBEVSAMQFT2FNTWNWJBPI/graph.json","fetch_events":"https://pith.science/api/pith-number/WARRYYBEVSAMQFT2FNTWNWJBPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI/action/storage_attestation","attest_author":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI/action/author_attestation","sign_citation":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI/action/citation_signature","submit_replication":"https://pith.science/pith/WARRYYBEVSAMQFT2FNTWNWJBPI/action/replication_record"}},"created_at":"2026-07-05T02:53:05.509613+00:00","updated_at":"2026-07-05T02:53:05.509613+00:00"}