{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W7I6JLO4JCZPGJFGKF5PIURHNI","short_pith_number":"pith:W7I6JLO4","schema_version":"1.0","canonical_sha256":"b7d1e4addc48b2f324a6517af452276a088baff2e8e4a9ce394935aec28d278d","source":{"kind":"arxiv","id":"2409.00933","version":1},"attestation_state":"computed","paper":{"title":"SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dake Guo, Dongchao Yang, Fenglong Xie, Haohan Guo, Helen Meng, Kun Xie, Xixin Wu","submitted_at":"2024-09-02T04:13:20Z","abstract_excerpt":"The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It compresses speech into a shorter, multi-stream discrete semantic sequence with multiple tokens at each frame. Meanwhile, the ordered product quantization is proposed to constrain this sequence into an ordered representation. It can be applied with a multi-stream delayed LM to achieve better autoregressive generation along both time and stream axes in TTS. The expe"},"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":"2409.00933","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-02T04:13:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6f36e0c64e2d21de3ac9912c51a36809e29d530e6149fe19aedbd702872e4a06","abstract_canon_sha256":"aded0e7244f687f7a1a256c709655b1a7b4eef1207047fe70c87216f2a6540fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:55.463286Z","signature_b64":"wHU5D1RRuF10XDz2H9+ZYwvFSNK28OKqo+VxPRlUpD2mKaI5oEG8X4r3+HlpSvaZRckFZhZqqKP9QBjYYM18Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7d1e4addc48b2f324a6517af452276a088baff2e8e4a9ce394935aec28d278d","last_reissued_at":"2026-07-05T09:01:55.462812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:55.462812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dake Guo, Dongchao Yang, Fenglong Xie, Haohan Guo, Helen Meng, Kun Xie, Xixin Wu","submitted_at":"2024-09-02T04:13:20Z","abstract_excerpt":"The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It compresses speech into a shorter, multi-stream discrete semantic sequence with multiple tokens at each frame. Meanwhile, the ordered product quantization is proposed to constrain this sequence into an ordered representation. It can be applied with a multi-stream delayed LM to achieve better autoregressive generation along both time and stream axes in TTS. The expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00933","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/2409.00933/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":"2409.00933","created_at":"2026-07-05T09:01:55.462869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00933v1","created_at":"2026-07-05T09:01:55.462869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00933","created_at":"2026-07-05T09:01:55.462869+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7I6JLO4JCZP","created_at":"2026-07-05T09:01:55.462869+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7I6JLO4JCZPGJFG","created_at":"2026-07-05T09:01:55.462869+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7I6JLO4","created_at":"2026-07-05T09:01:55.462869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08667","citing_title":"A Unifying Perspective on Audio Generative Modeling: Latent Representations and Modeling Strategies","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI","json":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI.json","graph_json":"https://pith.science/api/pith-number/W7I6JLO4JCZPGJFGKF5PIURHNI/graph.json","events_json":"https://pith.science/api/pith-number/W7I6JLO4JCZPGJFGKF5PIURHNI/events.json","paper":"https://pith.science/paper/W7I6JLO4"},"agent_actions":{"view_html":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI","download_json":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI.json","view_paper":"https://pith.science/paper/W7I6JLO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00933&json=true","fetch_graph":"https://pith.science/api/pith-number/W7I6JLO4JCZPGJFGKF5PIURHNI/graph.json","fetch_events":"https://pith.science/api/pith-number/W7I6JLO4JCZPGJFGKF5PIURHNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI/action/storage_attestation","attest_author":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI/action/author_attestation","sign_citation":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI/action/citation_signature","submit_replication":"https://pith.science/pith/W7I6JLO4JCZPGJFGKF5PIURHNI/action/replication_record"}},"created_at":"2026-07-05T09:01:55.462869+00:00","updated_at":"2026-07-05T09:01:55.462869+00:00"}