{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TIKYLTPU7FKDJOCYF4NYK5EVXR","short_pith_number":"pith:TIKYLTPU","schema_version":"1.0","canonical_sha256":"9a1585cdf4f95434b8582f1b857495bc707d0a973a98909fbeca3f00faa859b9","source":{"kind":"arxiv","id":"2306.00814","version":3},"attestation_state":"computed","paper":{"title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hubert Siuzdak","submitted_at":"2023-06-01T15:40:32Z","abstract_excerpt":"Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations, resulting in reduntant and computionally-intensive upsampling operations. Fourier-based time-frequency representation is an appealing alternative, aligning more accurately with human auditory perception, and benefitting from well-established fast algorithms for its computation. Nevertheless, direct reconstruction of complex-valued spectrograms has been histori"},"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":"2306.00814","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-01T15:40:32Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"ad2c07ac4bfd83b51f2cd5da3bacc9175366a6361e186c91eadbcf2f9bb0c444","abstract_canon_sha256":"2d82272d1d00e5f90f860d857a4b99302347beb5be872a2d319a617dd7fb26e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:36.490004Z","signature_b64":"vlQxaF/IVc9j2zEmH+q+69Rf+gY7JQOntoXWHSn5gbDkXymFccKGhwjCgG9wzihB+cXyfAMgAc3Bd12Bf48HBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a1585cdf4f95434b8582f1b857495bc707d0a973a98909fbeca3f00faa859b9","last_reissued_at":"2026-07-05T08:24:36.489570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:36.489570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hubert Siuzdak","submitted_at":"2023-06-01T15:40:32Z","abstract_excerpt":"Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations, resulting in reduntant and computionally-intensive upsampling operations. Fourier-based time-frequency representation is an appealing alternative, aligning more accurately with human auditory perception, and benefitting from well-established fast algorithms for its computation. Nevertheless, direct reconstruction of complex-valued spectrograms has been histori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00814","kind":"arxiv","version":3},"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/2306.00814/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":"2306.00814","created_at":"2026-07-05T08:24:36.489625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00814v3","created_at":"2026-07-05T08:24:36.489625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00814","created_at":"2026-07-05T08:24:36.489625+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIKYLTPU7FKD","created_at":"2026-07-05T08:24:36.489625+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIKYLTPU7FKDJOCY","created_at":"2026-07-05T08:24:36.489625+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIKYLTPU","created_at":"2026-07-05T08:24:36.489625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":167,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23176","citing_title":"Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23190","citing_title":"FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21372","citing_title":"NAC: Neural Action Codec for Vision-Language-Action Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17806","citing_title":"PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11611","citing_title":"SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09048","citing_title":"BareWave: Waveform-Native Flow-Matching Text-to-Speech","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24708","citing_title":"SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14606","citing_title":"UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR","json":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR.json","graph_json":"https://pith.science/api/pith-number/TIKYLTPU7FKDJOCYF4NYK5EVXR/graph.json","events_json":"https://pith.science/api/pith-number/TIKYLTPU7FKDJOCYF4NYK5EVXR/events.json","paper":"https://pith.science/paper/TIKYLTPU"},"agent_actions":{"view_html":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR","download_json":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR.json","view_paper":"https://pith.science/paper/TIKYLTPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00814&json=true","fetch_graph":"https://pith.science/api/pith-number/TIKYLTPU7FKDJOCYF4NYK5EVXR/graph.json","fetch_events":"https://pith.science/api/pith-number/TIKYLTPU7FKDJOCYF4NYK5EVXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR/action/storage_attestation","attest_author":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR/action/author_attestation","sign_citation":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR/action/citation_signature","submit_replication":"https://pith.science/pith/TIKYLTPU7FKDJOCYF4NYK5EVXR/action/replication_record"}},"created_at":"2026-07-05T08:24:36.489625+00:00","updated_at":"2026-07-05T08:24:36.489625+00:00"}