{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BWMWUCIKXOLFJDRDIYMPJPYAQZ","short_pith_number":"pith:BWMWUCIK","schema_version":"1.0","canonical_sha256":"0d996a090abb96548e234618f4bf0086742923bc39e7d307daec84d52ac0c1b7","source":{"kind":"arxiv","id":"2410.17081","version":2},"attestation_state":"computed","paper":{"title":"Continuous Speech Tokenizer in Text To Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ruobing Xie, Xingwu Sun, Yixing Li, Yu Cheng, Zhanhui Kang","submitted_at":"2024-10-22T15:02:37Z","abstract_excerpt":"The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint training with text and have good compression efficiency. However, we found that the discrete speech tokenizer still suffers from information loss. Therefore, we propose a simple yet effective continuous speech tokenizer named Cont-SPT, and a text-to-speech model based on continuous speech tokens. Our results show that the speech language model based on the c"},"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":"2410.17081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-22T15:02:37Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e9aa6abf5b4576c2e37dd6dbb3c52a45188bd965aeb4d6ec1d68b1dd266962d4","abstract_canon_sha256":"54ff05c61504dc3ef8bf2e2e7db23f4202d63cafc94760e9a586b390ceafcca9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:49.693805Z","signature_b64":"TCmkGOjCTgh72dFwvXrjPptIJL2AFqrPxGccWcKU0ce27qGgTZDK1PsZqp2kGVMJOhtZOlpF+jSZACzEh9lKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d996a090abb96548e234618f4bf0086742923bc39e7d307daec84d52ac0c1b7","last_reissued_at":"2026-07-05T10:41:49.693309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:49.693309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Speech Tokenizer in Text To Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ruobing Xie, Xingwu Sun, Yixing Li, Yu Cheng, Zhanhui Kang","submitted_at":"2024-10-22T15:02:37Z","abstract_excerpt":"The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint training with text and have good compression efficiency. However, we found that the discrete speech tokenizer still suffers from information loss. Therefore, we propose a simple yet effective continuous speech tokenizer named Cont-SPT, and a text-to-speech model based on continuous speech tokens. Our results show that the speech language model based on the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17081","kind":"arxiv","version":2},"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/2410.17081/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":"2410.17081","created_at":"2026-07-05T10:41:49.693377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17081v2","created_at":"2026-07-05T10:41:49.693377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17081","created_at":"2026-07-05T10:41:49.693377+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWMWUCIKXOLF","created_at":"2026-07-05T10:41:49.693377+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWMWUCIKXOLFJDRD","created_at":"2026-07-05T10:41:49.693377+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWMWUCIK","created_at":"2026-07-05T10:41:49.693377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17863","citing_title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ","json":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ.json","graph_json":"https://pith.science/api/pith-number/BWMWUCIKXOLFJDRDIYMPJPYAQZ/graph.json","events_json":"https://pith.science/api/pith-number/BWMWUCIKXOLFJDRDIYMPJPYAQZ/events.json","paper":"https://pith.science/paper/BWMWUCIK"},"agent_actions":{"view_html":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ","download_json":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ.json","view_paper":"https://pith.science/paper/BWMWUCIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17081&json=true","fetch_graph":"https://pith.science/api/pith-number/BWMWUCIKXOLFJDRDIYMPJPYAQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BWMWUCIKXOLFJDRDIYMPJPYAQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ/action/storage_attestation","attest_author":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ/action/author_attestation","sign_citation":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ/action/citation_signature","submit_replication":"https://pith.science/pith/BWMWUCIKXOLFJDRDIYMPJPYAQZ/action/replication_record"}},"created_at":"2026-07-05T10:41:49.693377+00:00","updated_at":"2026-07-05T10:41:49.693377+00:00"}