{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAK2WEZCPPTGZ5XP4IKIIDB7MR","short_pith_number":"pith:FAK2WEZC","schema_version":"1.0","canonical_sha256":"2815ab13227be66cf6efe214840c3f64494919ef8700c1102204a9129b3c7869","source":{"kind":"arxiv","id":"2507.18897","version":1},"attestation_state":"computed","paper":{"title":"HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jing Yang, Rongkun Xue, Shuai Hu, Yazhe Niu, Yongqiang Yao, Zixin Yin","submitted_at":"2025-07-25T02:44:30Z","abstract_excerpt":"Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional codecs pose significant challenges. In this paper, we introduce HH-Codec, a neural codec that achieves extreme compression at 24 tokens per second for 24 kHz audio while relying on single-quantizer inference. Our approach involves a carefully designed Vector Quantization space for Spoken Language Modeling, optimizing compression efficiency while minimizing infor"},"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":"2507.18897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T02:44:30Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"5e123cb3065917b3d133bbf1bf51aef094e3d2831b17d6ff615ee45806d1e004","abstract_canon_sha256":"dfc668d3a4a6de3c39ad96b20e9dc9baac7bf6457c8a759601e5958ed1128088"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:15.763369Z","signature_b64":"dU93A2WdVZCVbfSU0Hh/PWmTk1RRmh/+YqmD98umGhuhyJ+C3v5bPMVW9/PsNWpa/D356tPVbV4r3CJxBDcuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2815ab13227be66cf6efe214840c3f64494919ef8700c1102204a9129b3c7869","last_reissued_at":"2026-07-05T11:43:15.762922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:15.762922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jing Yang, Rongkun Xue, Shuai Hu, Yazhe Niu, Yongqiang Yao, Zixin Yin","submitted_at":"2025-07-25T02:44:30Z","abstract_excerpt":"Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional codecs pose significant challenges. In this paper, we introduce HH-Codec, a neural codec that achieves extreme compression at 24 tokens per second for 24 kHz audio while relying on single-quantizer inference. Our approach involves a carefully designed Vector Quantization space for Spoken Language Modeling, optimizing compression efficiency while minimizing infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18897","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/2507.18897/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":"2507.18897","created_at":"2026-07-05T11:43:15.762978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18897v1","created_at":"2026-07-05T11:43:15.762978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18897","created_at":"2026-07-05T11:43:15.762978+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAK2WEZCPPTG","created_at":"2026-07-05T11:43:15.762978+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAK2WEZCPPTGZ5XP","created_at":"2026-07-05T11:43:15.762978+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAK2WEZC","created_at":"2026-07-05T11:43:15.762978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04418","citing_title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14806","citing_title":"Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR","json":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR.json","graph_json":"https://pith.science/api/pith-number/FAK2WEZCPPTGZ5XP4IKIIDB7MR/graph.json","events_json":"https://pith.science/api/pith-number/FAK2WEZCPPTGZ5XP4IKIIDB7MR/events.json","paper":"https://pith.science/paper/FAK2WEZC"},"agent_actions":{"view_html":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR","download_json":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR.json","view_paper":"https://pith.science/paper/FAK2WEZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18897&json=true","fetch_graph":"https://pith.science/api/pith-number/FAK2WEZCPPTGZ5XP4IKIIDB7MR/graph.json","fetch_events":"https://pith.science/api/pith-number/FAK2WEZCPPTGZ5XP4IKIIDB7MR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR/action/storage_attestation","attest_author":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR/action/author_attestation","sign_citation":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR/action/citation_signature","submit_replication":"https://pith.science/pith/FAK2WEZCPPTGZ5XP4IKIIDB7MR/action/replication_record"}},"created_at":"2026-07-05T11:43:15.762978+00:00","updated_at":"2026-07-05T11:43:15.762978+00:00"}