{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T7WQMN44URU4O4T5IUJB3HDTUZ","short_pith_number":"pith:T7WQMN44","schema_version":"1.0","canonical_sha256":"9fed06379ca469c7727d45121d9c73a654c425df6de3492a9885b6bdb9969b64","source":{"kind":"arxiv","id":"2607.23811","version":1},"attestation_state":"computed","paper":{"title":"Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Chung-Cheng Chiu, Dipjyoti Paul, Dongseong Hwang, Emad Soroush, Kaan Elgin, Prasanth Yadla, Ramya Rasipuram, Shifas Padinjaru Veettil, Sivanand Achanta, Tyler Johnson, Zhifeng Chen","submitted_at":"2026-07-26T19:20:01Z","abstract_excerpt":"Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming enco"},"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":"2607.23811","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T19:20:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c58b5a9d6f45e8f398b7bbdf92b81e84ece0037c71a9179dfd69ae8fd2d3fde1","abstract_canon_sha256":"c84187c979e988dc0065ee34c615a12fbdeb3df488910004cfca6259f9ae6d88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:12.381677Z","signature_b64":"IWGH8Hj0Ne65o4zDhqvkrNPdtM5vSOZOrJfJ9hq+x5UShAsMn3rZjsidEXOgirGhN5ksy9qg5GYggjSnFghCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fed06379ca469c7727d45121d9c73a654c425df6de3492a9885b6bdb9969b64","last_reissued_at":"2026-07-28T01:23:12.380862Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:12.380862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Chung-Cheng Chiu, Dipjyoti Paul, Dongseong Hwang, Emad Soroush, Kaan Elgin, Prasanth Yadla, Ramya Rasipuram, Shifas Padinjaru Veettil, Sivanand Achanta, Tyler Johnson, Zhifeng Chen","submitted_at":"2026-07-26T19:20:01Z","abstract_excerpt":"Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23811","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/2607.23811/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":"2607.23811","created_at":"2026-07-28T01:23:12.381272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23811v1","created_at":"2026-07-28T01:23:12.381272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23811","created_at":"2026-07-28T01:23:12.381272+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7WQMN44URU4","created_at":"2026-07-28T01:23:12.381272+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7WQMN44URU4O4T5","created_at":"2026-07-28T01:23:12.381272+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7WQMN44","created_at":"2026-07-28T01:23:12.381272+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/T7WQMN44URU4O4T5IUJB3HDTUZ","json":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ.json","graph_json":"https://pith.science/api/pith-number/T7WQMN44URU4O4T5IUJB3HDTUZ/graph.json","events_json":"https://pith.science/api/pith-number/T7WQMN44URU4O4T5IUJB3HDTUZ/events.json","paper":"https://pith.science/paper/T7WQMN44"},"agent_actions":{"view_html":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ","download_json":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ.json","view_paper":"https://pith.science/paper/T7WQMN44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23811&json=true","fetch_graph":"https://pith.science/api/pith-number/T7WQMN44URU4O4T5IUJB3HDTUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/T7WQMN44URU4O4T5IUJB3HDTUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ/action/storage_attestation","attest_author":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ/action/author_attestation","sign_citation":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ/action/citation_signature","submit_replication":"https://pith.science/pith/T7WQMN44URU4O4T5IUJB3HDTUZ/action/replication_record"}},"created_at":"2026-07-28T01:23:12.381272+00:00","updated_at":"2026-07-28T01:23:12.381272+00:00"}