{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NCI7F63PSLJXH2ODTXUO2GP373","short_pith_number":"pith:NCI7F63P","schema_version":"1.0","canonical_sha256":"6891f2fb6f92d373e9c39de8ed19fbfed8082633767099d32d79209b521e73d1","source":{"kind":"arxiv","id":"2411.11258","version":1},"attestation_state":"computed","paper":{"title":"ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hui-Peng Du, Xiao-Hang Jiang, Yang Ai, Ye-Xin Lu, Zhen-Hua Ling","submitted_at":"2024-11-18T03:22:34Z","abstract_excerpt":"This paper proposes ESTVocoder, a novel excitation-spectral-transformed neural vocoder within the framework of source-filter theory. The ESTVocoder transforms the amplitude and phase spectra of the excitation into the corresponding speech amplitude and phase spectra using a neural filter whose backbone is ConvNeXt v2 blocks. Finally, the speech waveform is reconstructed through the inverse short-time Fourier transform (ISTFT). The excitation is constructed based on the F0: for voiced segments, it contains full harmonic information, while for unvoiced segments, it is represented by noise. The e"},"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":"2411.11258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-18T03:22:34Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"efa94d42598c99dd38f56cedffdd7e9591063a4241445308fa5b00c08c5d4072","abstract_canon_sha256":"37f16d25160af0115be194d046e1e6b3b1503751813f5578fbe15d717c73bb93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:53.718041Z","signature_b64":"fUbiieCDShYE/T1lQ+Q0GEW6/t7rBuoeP8HJBpBSW48z0GVpz/adS+eT72+/dGDLmFePzWzwkZX8bj1FJcHuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6891f2fb6f92d373e9c39de8ed19fbfed8082633767099d32d79209b521e73d1","last_reissued_at":"2026-07-05T09:36:53.717570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:53.717570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hui-Peng Du, Xiao-Hang Jiang, Yang Ai, Ye-Xin Lu, Zhen-Hua Ling","submitted_at":"2024-11-18T03:22:34Z","abstract_excerpt":"This paper proposes ESTVocoder, a novel excitation-spectral-transformed neural vocoder within the framework of source-filter theory. The ESTVocoder transforms the amplitude and phase spectra of the excitation into the corresponding speech amplitude and phase spectra using a neural filter whose backbone is ConvNeXt v2 blocks. Finally, the speech waveform is reconstructed through the inverse short-time Fourier transform (ISTFT). The excitation is constructed based on the F0: for voiced segments, it contains full harmonic information, while for unvoiced segments, it is represented by noise. The e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11258","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/2411.11258/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":"2411.11258","created_at":"2026-07-05T09:36:53.717623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11258v1","created_at":"2026-07-05T09:36:53.717623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11258","created_at":"2026-07-05T09:36:53.717623+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCI7F63PSLJX","created_at":"2026-07-05T09:36:53.717623+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCI7F63PSLJXH2OD","created_at":"2026-07-05T09:36:53.717623+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCI7F63P","created_at":"2026-07-05T09:36:53.717623+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/NCI7F63PSLJXH2ODTXUO2GP373","json":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373.json","graph_json":"https://pith.science/api/pith-number/NCI7F63PSLJXH2ODTXUO2GP373/graph.json","events_json":"https://pith.science/api/pith-number/NCI7F63PSLJXH2ODTXUO2GP373/events.json","paper":"https://pith.science/paper/NCI7F63P"},"agent_actions":{"view_html":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373","download_json":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373.json","view_paper":"https://pith.science/paper/NCI7F63P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11258&json=true","fetch_graph":"https://pith.science/api/pith-number/NCI7F63PSLJXH2ODTXUO2GP373/graph.json","fetch_events":"https://pith.science/api/pith-number/NCI7F63PSLJXH2ODTXUO2GP373/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373/action/storage_attestation","attest_author":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373/action/author_attestation","sign_citation":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373/action/citation_signature","submit_replication":"https://pith.science/pith/NCI7F63PSLJXH2ODTXUO2GP373/action/replication_record"}},"created_at":"2026-07-05T09:36:53.717623+00:00","updated_at":"2026-07-05T09:36:53.717623+00:00"}