{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_8c44d060b0f6c2200d9f97a58fa64463929a11587a13f36d07b43e37e34f8a77","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_8c44d060b0f6c2200d9f97a58fa64463929a11587a13f36d07b43e37e34f8a77","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fad444990d450c05fc2faaffda3365bc58ef3243adaf8b7b676850d7d5ba3d21","published":"Fri, 29 May 2026 00:00:00 -0400","receipt_hash":"fad444990d450c05fc2faaffda3365bc58ef3243adaf8b7b676850d7d5ba3d21","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"fad444990d450c05fc2faaffda3365bc58ef3243adaf8b7b676850d7d5ba3d21","observed_at":"2026-05-29T04:43:58.478092Z","parent_run_hash":"0fcd87efcfe67ccb9952f747541debc16793919a4d20fd71ca0ad5516a0a13ee","published":"Fri, 29 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.29948v1 Announce Type: cross \nAbstract: Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements simultaneously, leading to increased architectural complexity and more involved training designs. We propose HoliTok, a continuous Holistic speech Tokenization model designed for unified generation-understanding modeling. HoliTok encodes 48~kHz speech into a compact 25~Hz sequence of 128-dimensional latents. It is trained with a progressive strategy that jointly preserves signal-level fidelity, incorporates semantic information, and maintains strong latent learnability. Based on this tokenization, we build a unified AR+DiT model for speech synthesis and recognition, where the same latent sequence supports both generation-specific and unified generation-understanding tasks. Experiments show that HoliTok ach","title":"HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding","url":"https://arxiv.org/abs/2605.29948","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.29948v1 Announce Type: cross \nAbstract: Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements simultaneously, leading to increased architectural complexity and more involved training designs. We propose HoliTok, a continuous Holistic speech Tokenization model designed for unified generation-understanding modeling. HoliTok encodes 48~kHz speech into a compact 25~Hz sequence of 128-dimensional latents. It is trained with a progressive strategy that jointly preserves signal-level fidelity, incorporates semantic information, and maintains strong latent learnability. Based on this tokenization, we build a unified AR+DiT model for speech synthesis and recognition, where the same latent sequence supports both generation-specific and unified generation-understanding tasks. Experiments show that HoliTok ach","title":"HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-29T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.29948"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4fdc27356b701fd380541c6ad1711818f3836ffae12b5fb40af9f9420050c8214e8b8bcd4cefdb858d1a4c7988bc869f1273c331e908e6d42579df1b8491000a","signer":"crovia.substrate","subject":{"observed_at":"2026-05-29T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.29948"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"91b301e9e1b2935c9faceccd957c55d8dbddee01eeb3fa3ce59584eea8cc9136","leaf_index":157937,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"64fe4a98d448411cb10d020cc7204d9e12910abeb5965ff1d7b8e05ebf23f966","side":"left"},{"sibling":"1eaeea7120c22f85a3593a11ba43a3272b15dc799277ea11ebc15d206e93c88a","side":"right"},{"sibling":"db9746f1453e52746468fb2bab2dedf7aac00fd89e97211260461cc8124b552a","side":"right"},{"sibling":"3bea022b2e468abfc3407780e3cb4fcc146146cb60a052417a9ba9bee56ff4b5","side":"right"},{"sibling":"7bd4ea5f68cece801ee03d952f0185dff485f6f2106a996c8ba5c2bb950d83a0","side":"left"},{"sibling":"890e5d094ab85d72dd213fa54c767fff10301cea5e71d124fb2bd8c9ef7d6808","side":"left"},{"sibling":"e968a3113c7ee604862ad79b0dd0c6684830b4ce02bb4fc025a91bcc16a9be3f","side":"left"},{"sibling":"8fe4932bfd0d62d46f26dbb29e67a452b7b1c018843a618ec931b6043bac464c","side":"left"},{"sibling":"291a37d6414d385e45486ef4725ce7087043d900d04f90b309d04bd876c338e5","side":"right"},{"sibling":"1dcc44e23fbb0218b13591e4b584eca3600dcf365769cb741e0ecd33b25b8c56","side":"right"},{"sibling":"fcf16a6f44025801f5b83e928acce764352ddbc06ae3043d8cde9a409933e6d8","side":"right"},{"sibling":"78982294dee68f9db9288c64d7e507c7865fda96e1b6f7ccff5c8bb152e93c49","side":"left"},{"sibling":"995b421824624a8282c7f44e64c64ee35344800f477ae1845b41be14d3fab94c","side":"right"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"eef0e8906a749d3470f89beeedc723f37a5737010bbb0dcc7cf91515338e5a3e","side":"right"},{"sibling":"1a07e481a9407d71aad078ce854cdeee362163c887fe10f889b0ecf0b5e749ad","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":158251,"merkle_root":"485e6b31fe60c8beba5b394808c7e4c32448b2ff65c2482c480ca0e2a2eda718","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260529T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-29T05:37:37Z","sig_algorithm":"ed25519","signature":"bbf9f005201182fce4f9d94c7a9d01a508b56daf7d9611bd73514f5f616bc059d0e5e1f2edfc95716e6fe08ef5fae38b558cbf7f2fd8f9d5dfe4c34a54c83005","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_8c44d060b0f6c2200d9f97a58fa64463929a11587a13f36d07b43e37e34f8a77"}}