{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H4GGQSI7SCDJLXSI2AX3T6PXXI","short_pith_number":"pith:H4GGQSI7","schema_version":"1.0","canonical_sha256":"3f0c68491f908695de48d02fb9f9f7ba3623d24e648bfe3319dc3961d3bb94e6","source":{"kind":"arxiv","id":"2404.00791","version":1},"attestation_state":"computed","paper":{"title":"Personalized Neural Speech Codec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haici Yang, Inseon Jang, Minje Kim, Seungkwon Beack, Wootaek Lim","submitted_at":"2024-03-31T20:32:40Z","abstract_excerpt":"In this paper, we propose a personalized neural speech codec, envisioning that personalization can reduce the model complexity or improve perceptual speech quality. Despite the common usage of speech codecs where only a single talker is involved on each side of the communication, personalizing a codec for the specific user has rarely been explored in the literature. First, we assume speakers can be grouped into smaller subsets based on their perceptual similarity. Then, we also postulate that a group-specific codec can focus on the group's speech characteristics to improve its perceptual quali"},"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":"2404.00791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-31T20:32:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2a13be2f2317024c4dccabb4247a7c6ea22c07134d52055f780c65c6aeba7422","abstract_canon_sha256":"52995a209083c36cfffc9f8333a5e8dc851c3865ef285db109d768341c6d2d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:56.702018Z","signature_b64":"Xrmn+XEOeuzXyJGfx4+QEwyV0g0SMd4VJ0uimXtUAJOaO0PXQW68JZh98+Lzujvp8X8y0SwtBGyUaHDmYmCHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0c68491f908695de48d02fb9f9f7ba3623d24e648bfe3319dc3961d3bb94e6","last_reissued_at":"2026-07-05T08:02:56.701378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:56.701378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Neural Speech Codec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haici Yang, Inseon Jang, Minje Kim, Seungkwon Beack, Wootaek Lim","submitted_at":"2024-03-31T20:32:40Z","abstract_excerpt":"In this paper, we propose a personalized neural speech codec, envisioning that personalization can reduce the model complexity or improve perceptual speech quality. Despite the common usage of speech codecs where only a single talker is involved on each side of the communication, personalizing a codec for the specific user has rarely been explored in the literature. First, we assume speakers can be grouped into smaller subsets based on their perceptual similarity. Then, we also postulate that a group-specific codec can focus on the group's speech characteristics to improve its perceptual quali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00791","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/2404.00791/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":"2404.00791","created_at":"2026-07-05T08:02:56.701450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00791v1","created_at":"2026-07-05T08:02:56.701450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00791","created_at":"2026-07-05T08:02:56.701450+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4GGQSI7SCDJ","created_at":"2026-07-05T08:02:56.701450+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4GGQSI7SCDJLXSI","created_at":"2026-07-05T08:02:56.701450+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4GGQSI7","created_at":"2026-07-05T08:02:56.701450+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/H4GGQSI7SCDJLXSI2AX3T6PXXI","json":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI.json","graph_json":"https://pith.science/api/pith-number/H4GGQSI7SCDJLXSI2AX3T6PXXI/graph.json","events_json":"https://pith.science/api/pith-number/H4GGQSI7SCDJLXSI2AX3T6PXXI/events.json","paper":"https://pith.science/paper/H4GGQSI7"},"agent_actions":{"view_html":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI","download_json":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI.json","view_paper":"https://pith.science/paper/H4GGQSI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00791&json=true","fetch_graph":"https://pith.science/api/pith-number/H4GGQSI7SCDJLXSI2AX3T6PXXI/graph.json","fetch_events":"https://pith.science/api/pith-number/H4GGQSI7SCDJLXSI2AX3T6PXXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI/action/storage_attestation","attest_author":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI/action/author_attestation","sign_citation":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI/action/citation_signature","submit_replication":"https://pith.science/pith/H4GGQSI7SCDJLXSI2AX3T6PXXI/action/replication_record"}},"created_at":"2026-07-05T08:02:56.701450+00:00","updated_at":"2026-07-05T08:02:56.701450+00:00"}