{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SH55XNJG5726MYK3VIWKN4F4R3","short_pith_number":"pith:SH55XNJG","schema_version":"1.0","canonical_sha256":"91fbdbb526eff5e6615baa2ca6f0bc8efc4ee2d5a4f2c3f85de4ec76f1743e1c","source":{"kind":"arxiv","id":"2404.02702","version":3},"attestation_state":"computed","paper":{"title":"PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Hongbin Zhou, Jianhao Ye, Jianjun Zhao, Jixun Yao, Lei Ma, Xiang Zhang, Yanni Hu, Yuguang Yang, Yu Pan","submitted_at":"2024-04-03T13:00:08Z","abstract_excerpt":"Neural speech codecs have recently emerged as a focal point in the fields of speech compression and generation. Despite this progress, achieving high-quality speech reconstruction under low-bitrate scenarios remains a significant challenge. In this paper, we propose PSCodec, a series of neural speech codecs based on prompt encoders, comprising PSCodec-Base, PSCodec-DRL-ICT, and PSCodec-CasAN, which are capable of delivering high-performance speech reconstruction with low bandwidths. Specifically, we first introduce PSCodec-Base, which leverages a pretrained speaker verification model-based pro"},"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":"2404.02702","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-04-03T13:00:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f95cf87dc3addc49455778959417b0816ece63211c6a0026f9f0dd8c9ccdeafc","abstract_canon_sha256":"91eee54f643611300f60d72bff998366c9ca060c10040ffdfc9c4a496da272e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:25.318103Z","signature_b64":"gRlCTbD3Rq21fVGM6wQN8WeD05oNIdu6075vX3T8Qoq045DJjY6dzY6gZqs1aS1tAB7k3L+IqMh46hOfJQj9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91fbdbb526eff5e6615baa2ca6f0bc8efc4ee2d5a4f2c3f85de4ec76f1743e1c","last_reissued_at":"2026-07-05T09:38:25.317644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:25.317644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Hongbin Zhou, Jianhao Ye, Jianjun Zhao, Jixun Yao, Lei Ma, Xiang Zhang, Yanni Hu, Yuguang Yang, Yu Pan","submitted_at":"2024-04-03T13:00:08Z","abstract_excerpt":"Neural speech codecs have recently emerged as a focal point in the fields of speech compression and generation. Despite this progress, achieving high-quality speech reconstruction under low-bitrate scenarios remains a significant challenge. In this paper, we propose PSCodec, a series of neural speech codecs based on prompt encoders, comprising PSCodec-Base, PSCodec-DRL-ICT, and PSCodec-CasAN, which are capable of delivering high-performance speech reconstruction with low bandwidths. Specifically, we first introduce PSCodec-Base, which leverages a pretrained speaker verification model-based pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02702","kind":"arxiv","version":3},"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/2404.02702/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":"2404.02702","created_at":"2026-07-05T09:38:25.317703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02702v3","created_at":"2026-07-05T09:38:25.317703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02702","created_at":"2026-07-05T09:38:25.317703+00:00"},{"alias_kind":"pith_short_12","alias_value":"SH55XNJG5726","created_at":"2026-07-05T09:38:25.317703+00:00"},{"alias_kind":"pith_short_16","alias_value":"SH55XNJG5726MYK3","created_at":"2026-07-05T09:38:25.317703+00:00"},{"alias_kind":"pith_short_8","alias_value":"SH55XNJG","created_at":"2026-07-05T09:38:25.317703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04418","citing_title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19541","citing_title":"Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3","json":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3.json","graph_json":"https://pith.science/api/pith-number/SH55XNJG5726MYK3VIWKN4F4R3/graph.json","events_json":"https://pith.science/api/pith-number/SH55XNJG5726MYK3VIWKN4F4R3/events.json","paper":"https://pith.science/paper/SH55XNJG"},"agent_actions":{"view_html":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3","download_json":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3.json","view_paper":"https://pith.science/paper/SH55XNJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02702&json=true","fetch_graph":"https://pith.science/api/pith-number/SH55XNJG5726MYK3VIWKN4F4R3/graph.json","fetch_events":"https://pith.science/api/pith-number/SH55XNJG5726MYK3VIWKN4F4R3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3/action/storage_attestation","attest_author":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3/action/author_attestation","sign_citation":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3/action/citation_signature","submit_replication":"https://pith.science/pith/SH55XNJG5726MYK3VIWKN4F4R3/action/replication_record"}},"created_at":"2026-07-05T09:38:25.317703+00:00","updated_at":"2026-07-05T09:38:25.317703+00:00"}