{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IR5A4OFP2DL4NNGIXCVF3VWAW7","short_pith_number":"pith:IR5A4OFP","schema_version":"1.0","canonical_sha256":"447a0e38afd0d7c6b4c8b8aa5dd6c0b7f6b6ed790ca5a4af377b3b7ae9c0f41d","source":{"kind":"arxiv","id":"2606.11631","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Neural Speech Compression from a Rate-Distortion Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fengxi Zhang, Jun Xu, Li Song, Wenjun Zhang, Yuhan Liu, Zhengxue Cheng","submitted_at":"2026-06-10T03:49:54Z","abstract_excerpt":"Learning-based speech compression has achieved promising low-bitrate performance, but many neural speech codecs still describe quantized latents with preset-rate discrete symbols or apply entropy coding only after symbol generation. Such designs decouple representation learning from probability modeling, limiting their ability to exploit the non-uniform usage and temporal dependencies of learned speech latents. In this paper, we benchmark neural speech compression from a rate--distortion perspective and further investigate entropy-constrained coding for low-bitrate speech compression. We first"},"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":"2606.11631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-10T03:49:54Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e417fd5ed6e8abddfd1e42faa5eb063a9f21867ed19bc4dea965b4248043dfff","abstract_canon_sha256":"2e3cbfd7d8d94447e279fa2db8a56b24ff52bcf0c7d87eaa128e4502abd1649e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:59.935729Z","signature_b64":"6NdqgvX1VNEGgFApb5uCjjT1sZF25EzsMZtOo12yiT7kXIaI8YXIqdzpi6QJSSD9cyOZAK2Ke+0f/bBKra4XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"447a0e38afd0d7c6b4c8b8aa5dd6c0b7f6b6ed790ca5a4af377b3b7ae9c0f41d","last_reissued_at":"2026-06-11T01:09:59.934920Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:59.934920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Neural Speech Compression from a Rate-Distortion Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Fengxi Zhang, Jun Xu, Li Song, Wenjun Zhang, Yuhan Liu, Zhengxue Cheng","submitted_at":"2026-06-10T03:49:54Z","abstract_excerpt":"Learning-based speech compression has achieved promising low-bitrate performance, but many neural speech codecs still describe quantized latents with preset-rate discrete symbols or apply entropy coding only after symbol generation. Such designs decouple representation learning from probability modeling, limiting their ability to exploit the non-uniform usage and temporal dependencies of learned speech latents. In this paper, we benchmark neural speech compression from a rate--distortion perspective and further investigate entropy-constrained coding for low-bitrate speech compression. We first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11631","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/2606.11631/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":"2606.11631","created_at":"2026-06-11T01:09:59.935058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11631v1","created_at":"2026-06-11T01:09:59.935058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11631","created_at":"2026-06-11T01:09:59.935058+00:00"},{"alias_kind":"pith_short_12","alias_value":"IR5A4OFP2DL4","created_at":"2026-06-11T01:09:59.935058+00:00"},{"alias_kind":"pith_short_16","alias_value":"IR5A4OFP2DL4NNGI","created_at":"2026-06-11T01:09:59.935058+00:00"},{"alias_kind":"pith_short_8","alias_value":"IR5A4OFP","created_at":"2026-06-11T01:09:59.935058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7","json":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7.json","graph_json":"https://pith.science/api/pith-number/IR5A4OFP2DL4NNGIXCVF3VWAW7/graph.json","events_json":"https://pith.science/api/pith-number/IR5A4OFP2DL4NNGIXCVF3VWAW7/events.json","paper":"https://pith.science/paper/IR5A4OFP"},"agent_actions":{"view_html":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7","download_json":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7.json","view_paper":"https://pith.science/paper/IR5A4OFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11631&json=true","fetch_graph":"https://pith.science/api/pith-number/IR5A4OFP2DL4NNGIXCVF3VWAW7/graph.json","fetch_events":"https://pith.science/api/pith-number/IR5A4OFP2DL4NNGIXCVF3VWAW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7/action/storage_attestation","attest_author":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7/action/author_attestation","sign_citation":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7/action/citation_signature","submit_replication":"https://pith.science/pith/IR5A4OFP2DL4NNGIXCVF3VWAW7/action/replication_record"}},"created_at":"2026-06-11T01:09:59.935058+00:00","updated_at":"2026-06-11T01:09:59.935058+00:00"}