{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VPCBV5CQ4CZBFPLBX3ETPKIP7C","short_pith_number":"pith:VPCBV5CQ","schema_version":"1.0","canonical_sha256":"abc41af450e0b212bd61bec937a90ff8b55a301785b20058f24cc43fcbbb2076","source":{"kind":"arxiv","id":"2201.09429","version":3},"attestation_state":"computed","paper":{"title":"End-to-End Neural Speech Coding for Real-Time Communications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chengyu Zheng, Huaying Xue, Xiulian Peng, Xue Jiang, Yan Lu, Yuan Zhang","submitted_at":"2022-01-24T03:06:30Z","abstract_excerpt":"Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low latency for RTC. It takes an encoder-temporal filtering-decoder paradigm that has seldom been investigated in audio coding. An interleaved structure is proposed for temporal filtering to capture both short-term and long-term temporal dependencies. Furthermore, with end-to-end optimization, the TFNet is jointly optimized with speech enhancement and packet loss"},"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":"2201.09429","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-24T03:06:30Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"3fd2c7958e48ff0ce96e65819d2e70fe0abe29186a7fcd71bd5bf92246e26351","abstract_canon_sha256":"5ac742eb5b61011a7f7b9bd096e208f944d7c068d3690b66af2a47ff09aacf7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:54.153921Z","signature_b64":"MJaWA8TsoZDXZpIGAoz9GB3yJj6WLccc3lUcJukLLA0aytPBKe43YpN1Xl1UgodM0ts431Von/suc1cuJnkuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abc41af450e0b212bd61bec937a90ff8b55a301785b20058f24cc43fcbbb2076","last_reissued_at":"2026-07-05T03:56:54.153517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:54.153517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Neural Speech Coding for Real-Time Communications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chengyu Zheng, Huaying Xue, Xiulian Peng, Xue Jiang, Yan Lu, Yuan Zhang","submitted_at":"2022-01-24T03:06:30Z","abstract_excerpt":"Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low latency for RTC. It takes an encoder-temporal filtering-decoder paradigm that has seldom been investigated in audio coding. An interleaved structure is proposed for temporal filtering to capture both short-term and long-term temporal dependencies. Furthermore, with end-to-end optimization, the TFNet is jointly optimized with speech enhancement and packet loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09429","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/2201.09429/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":"2201.09429","created_at":"2026-07-05T03:56:54.153578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.09429v3","created_at":"2026-07-05T03:56:54.153578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09429","created_at":"2026-07-05T03:56:54.153578+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPCBV5CQ4CZB","created_at":"2026-07-05T03:56:54.153578+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPCBV5CQ4CZBFPLB","created_at":"2026-07-05T03:56:54.153578+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPCBV5CQ","created_at":"2026-07-05T03:56:54.153578+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/VPCBV5CQ4CZBFPLBX3ETPKIP7C","json":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C.json","graph_json":"https://pith.science/api/pith-number/VPCBV5CQ4CZBFPLBX3ETPKIP7C/graph.json","events_json":"https://pith.science/api/pith-number/VPCBV5CQ4CZBFPLBX3ETPKIP7C/events.json","paper":"https://pith.science/paper/VPCBV5CQ"},"agent_actions":{"view_html":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C","download_json":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C.json","view_paper":"https://pith.science/paper/VPCBV5CQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.09429&json=true","fetch_graph":"https://pith.science/api/pith-number/VPCBV5CQ4CZBFPLBX3ETPKIP7C/graph.json","fetch_events":"https://pith.science/api/pith-number/VPCBV5CQ4CZBFPLBX3ETPKIP7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C/action/storage_attestation","attest_author":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C/action/author_attestation","sign_citation":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C/action/citation_signature","submit_replication":"https://pith.science/pith/VPCBV5CQ4CZBFPLBX3ETPKIP7C/action/replication_record"}},"created_at":"2026-07-05T03:56:54.153578+00:00","updated_at":"2026-07-05T03:56:54.153578+00:00"}