{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SS2BNS3PBFXZU5ERMA7WKVH5SC","short_pith_number":"pith:SS2BNS3P","schema_version":"1.0","canonical_sha256":"94b416cb6f096f9a7491603f6554fd9092efaa4eaa2261e5930d7a535b6b960b","source":{"kind":"arxiv","id":"2312.03491","version":1},"attestation_state":"computed","paper":{"title":"Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Guande He, Jun Zhu, Kaiwen Zheng, Xu Tan, Zehua Chen","submitted_at":"2023-12-06T13:31:55Z","abstract_excerpt":"In text-to-speech (TTS) synthesis, diffusion models have achieved promising generation quality. However, because of the pre-defined data-to-noise diffusion process, their prior distribution is restricted to a noisy representation, which provides little information of the generation target. In this work, we present a novel TTS system, Bridge-TTS, making the first attempt to substitute the noisy Gaussian prior in established diffusion-based TTS methods with a clean and deterministic one, which provides strong structural information of the target. Specifically, we leverage the latent representati"},"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":"2312.03491","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-06T13:31:55Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0bbae3555be271c95f71be216cf1a21233a6e085d08c2436415800baced79081","abstract_canon_sha256":"0d6f97e31a02e346437305587943237fdf36345d43fedc48d6d7ea98df9cc99c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:01.610868Z","signature_b64":"10loBZHWlLkQGXNnZvYCgL2tbQFgJq2ytMczoOB5UsJ8esILgvIDDYRURXfMO2MUqogXIWzi8Q4ZITX+a93LDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94b416cb6f096f9a7491603f6554fd9092efaa4eaa2261e5930d7a535b6b960b","last_reissued_at":"2026-07-05T07:43:01.610391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:01.610391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Guande He, Jun Zhu, Kaiwen Zheng, Xu Tan, Zehua Chen","submitted_at":"2023-12-06T13:31:55Z","abstract_excerpt":"In text-to-speech (TTS) synthesis, diffusion models have achieved promising generation quality. However, because of the pre-defined data-to-noise diffusion process, their prior distribution is restricted to a noisy representation, which provides little information of the generation target. In this work, we present a novel TTS system, Bridge-TTS, making the first attempt to substitute the noisy Gaussian prior in established diffusion-based TTS methods with a clean and deterministic one, which provides strong structural information of the target. Specifically, we leverage the latent representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03491","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/2312.03491/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":"2312.03491","created_at":"2026-07-05T07:43:01.610448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03491v1","created_at":"2026-07-05T07:43:01.610448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03491","created_at":"2026-07-05T07:43:01.610448+00:00"},{"alias_kind":"pith_short_12","alias_value":"SS2BNS3PBFXZ","created_at":"2026-07-05T07:43:01.610448+00:00"},{"alias_kind":"pith_short_16","alias_value":"SS2BNS3PBFXZU5ER","created_at":"2026-07-05T07:43:01.610448+00:00"},{"alias_kind":"pith_short_8","alias_value":"SS2BNS3P","created_at":"2026-07-05T07:43:01.610448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05575","citing_title":"SB-RF: Schr\\\"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancement","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05575","citing_title":"SB-RF: Schr\\\"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancement","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03119","citing_title":"GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18928","citing_title":"The Ensemble Schr{\\\"o}dinger Bridge filter for Nonlinear Data Assimilation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06327","citing_title":"A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC","json":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC.json","graph_json":"https://pith.science/api/pith-number/SS2BNS3PBFXZU5ERMA7WKVH5SC/graph.json","events_json":"https://pith.science/api/pith-number/SS2BNS3PBFXZU5ERMA7WKVH5SC/events.json","paper":"https://pith.science/paper/SS2BNS3P"},"agent_actions":{"view_html":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC","download_json":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC.json","view_paper":"https://pith.science/paper/SS2BNS3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03491&json=true","fetch_graph":"https://pith.science/api/pith-number/SS2BNS3PBFXZU5ERMA7WKVH5SC/graph.json","fetch_events":"https://pith.science/api/pith-number/SS2BNS3PBFXZU5ERMA7WKVH5SC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC/action/storage_attestation","attest_author":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC/action/author_attestation","sign_citation":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC/action/citation_signature","submit_replication":"https://pith.science/pith/SS2BNS3PBFXZU5ERMA7WKVH5SC/action/replication_record"}},"created_at":"2026-07-05T07:43:01.610448+00:00","updated_at":"2026-07-05T07:43:01.610448+00:00"}