{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5INSAGRMDHXOZD3L5DF5OOSSQK","short_pith_number":"pith:5INSAGRM","schema_version":"1.0","canonical_sha256":"ea1b201a2c19eeec8f6be8cbd73a528289f8b3de17923bc3d22818f6e018738d","source":{"kind":"arxiv","id":"2606.09048","version":1},"attestation_state":"computed","paper":{"title":"BareWave: Waveform-Native Flow-Matching Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chao-Hong Tan, Kejiang Chen, Nenghai Yu, Qian Chen, Wei Fan, Weiming Zhang, Wen Wang, Xiangang Li","submitted_at":"2026-06-08T05:36:42Z","abstract_excerpt":"Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality systems are still commonly built through an intermediate acoustic representation before waveform synthesis. In this work, we present BareWave, a fully waveform-native framework for direct text-to-wave generation in flow-matching TTS. We consider this setting to raise three training challenges: raw-waveform modeling lacks a strong pretrained representational scaffold, different stages of training benefit from different no"},"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":"2606.09048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T05:36:42Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"6821c6ad10831da7b4d663b9a40d067ad3ba9f32c5c415ff5f681de4b489f444","abstract_canon_sha256":"114d5766bb17ea0ad2f5b214aca088f465723a127822ec42dabf8166d59989ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:55.589805Z","signature_b64":"OHRu6L9e2EuifnFp5RiWO1HE+7BzFHnmM0KhXaK6XJ9jIJE+k/c/Fc4W4iH2SkQQXRquUjrGo2fO/lbyBJ84CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea1b201a2c19eeec8f6be8cbd73a528289f8b3de17923bc3d22818f6e018738d","last_reissued_at":"2026-06-09T02:07:55.588968Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:55.588968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BareWave: Waveform-Native Flow-Matching Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chao-Hong Tan, Kejiang Chen, Nenghai Yu, Qian Chen, Wei Fan, Weiming Zhang, Wen Wang, Xiangang Li","submitted_at":"2026-06-08T05:36:42Z","abstract_excerpt":"Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality systems are still commonly built through an intermediate acoustic representation before waveform synthesis. In this work, we present BareWave, a fully waveform-native framework for direct text-to-wave generation in flow-matching TTS. We consider this setting to raise three training challenges: raw-waveform modeling lacks a strong pretrained representational scaffold, different stages of training benefit from different no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09048","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/2606.09048/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":"2606.09048","created_at":"2026-06-09T02:07:55.589090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09048v1","created_at":"2026-06-09T02:07:55.589090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09048","created_at":"2026-06-09T02:07:55.589090+00:00"},{"alias_kind":"pith_short_12","alias_value":"5INSAGRMDHXO","created_at":"2026-06-09T02:07:55.589090+00:00"},{"alias_kind":"pith_short_16","alias_value":"5INSAGRMDHXOZD3L","created_at":"2026-06-09T02:07:55.589090+00:00"},{"alias_kind":"pith_short_8","alias_value":"5INSAGRM","created_at":"2026-06-09T02:07:55.589090+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/5INSAGRMDHXOZD3L5DF5OOSSQK","json":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK.json","graph_json":"https://pith.science/api/pith-number/5INSAGRMDHXOZD3L5DF5OOSSQK/graph.json","events_json":"https://pith.science/api/pith-number/5INSAGRMDHXOZD3L5DF5OOSSQK/events.json","paper":"https://pith.science/paper/5INSAGRM"},"agent_actions":{"view_html":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK","download_json":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK.json","view_paper":"https://pith.science/paper/5INSAGRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09048&json=true","fetch_graph":"https://pith.science/api/pith-number/5INSAGRMDHXOZD3L5DF5OOSSQK/graph.json","fetch_events":"https://pith.science/api/pith-number/5INSAGRMDHXOZD3L5DF5OOSSQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK/action/storage_attestation","attest_author":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK/action/author_attestation","sign_citation":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK/action/citation_signature","submit_replication":"https://pith.science/pith/5INSAGRMDHXOZD3L5DF5OOSSQK/action/replication_record"}},"created_at":"2026-06-09T02:07:55.589090+00:00","updated_at":"2026-06-09T02:07:55.589090+00:00"}