{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQR2LV67YJE4ICL4AALCQYCIG6","short_pith_number":"pith:ZQR2LV67","schema_version":"1.0","canonical_sha256":"cc23a5d7dfc249c4097c001628604837a2e5433636e6d87b01d309de7b5416a9","source":{"kind":"arxiv","id":"2606.11611","version":1},"attestation_state":"computed","paper":{"title":"SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daiyu Huang, Junbo Li, Jun Fang, Kaidi Wang, Lin Li, Peijie Chen, Qingyang Hong, Weijie Wu, Wenhao Guan, Zhuanling Zha","submitted_at":"2026-06-10T03:23:21Z","abstract_excerpt":"Zero-shot text-to-speech (TTS) relies on robust speech representations. However, current speech tokenizers face a fundamental trade-off: acoustic codecs preserve high-fidelity audio but lack linguistic constraints, causing content errors during generation, whereas semantic tokens from self-supervised learning (SSL) models ensure precise text alignment but discard some acoustic information. To bridge this gap, we propose SARA, a dual-stream VAE that directly fuses a frozen SSL semantic anchor with a dedicated residual acoustic encoder. This effectively mitigates the dilemma, creating an efficie"},"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":"2606.11611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-10T03:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"58d302beac40d7d53d686aa51689c3b29ae43833f0ad666ccd9b315b417312e7","abstract_canon_sha256":"4c217b3e287a8223573a3276b0084ce8a9ef3174f5b3933c42d04679ecd1f75a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:59.021845Z","signature_b64":"KpBwP7NzZxS0Mz+TGAkSRl8pqu+m7iyNLcrRil8FEwbxKLreZVDzBdhclmZCBGsMsLGBLMtaBfWMpoW2kcCUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc23a5d7dfc249c4097c001628604837a2e5433636e6d87b01d309de7b5416a9","last_reissued_at":"2026-06-11T01:09:59.020920Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:59.020920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daiyu Huang, Junbo Li, Jun Fang, Kaidi Wang, Lin Li, Peijie Chen, Qingyang Hong, Weijie Wu, Wenhao Guan, Zhuanling Zha","submitted_at":"2026-06-10T03:23:21Z","abstract_excerpt":"Zero-shot text-to-speech (TTS) relies on robust speech representations. However, current speech tokenizers face a fundamental trade-off: acoustic codecs preserve high-fidelity audio but lack linguistic constraints, causing content errors during generation, whereas semantic tokens from self-supervised learning (SSL) models ensure precise text alignment but discard some acoustic information. To bridge this gap, we propose SARA, a dual-stream VAE that directly fuses a frozen SSL semantic anchor with a dedicated residual acoustic encoder. This effectively mitigates the dilemma, creating an efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11611","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/2606.11611/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":"2606.11611","created_at":"2026-06-11T01:09:59.021046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11611v1","created_at":"2026-06-11T01:09:59.021046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11611","created_at":"2026-06-11T01:09:59.021046+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQR2LV67YJE4","created_at":"2026-06-11T01:09:59.021046+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQR2LV67YJE4ICL4","created_at":"2026-06-11T01:09:59.021046+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQR2LV67","created_at":"2026-06-11T01:09:59.021046+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/ZQR2LV67YJE4ICL4AALCQYCIG6","json":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6.json","graph_json":"https://pith.science/api/pith-number/ZQR2LV67YJE4ICL4AALCQYCIG6/graph.json","events_json":"https://pith.science/api/pith-number/ZQR2LV67YJE4ICL4AALCQYCIG6/events.json","paper":"https://pith.science/paper/ZQR2LV67"},"agent_actions":{"view_html":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6","download_json":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6.json","view_paper":"https://pith.science/paper/ZQR2LV67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11611&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQR2LV67YJE4ICL4AALCQYCIG6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQR2LV67YJE4ICL4AALCQYCIG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6/action/storage_attestation","attest_author":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6/action/author_attestation","sign_citation":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6/action/citation_signature","submit_replication":"https://pith.science/pith/ZQR2LV67YJE4ICL4AALCQYCIG6/action/replication_record"}},"created_at":"2026-06-11T01:09:59.021046+00:00","updated_at":"2026-06-11T01:09:59.021046+00:00"}