{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CMLEP6DZY53XY3QCE74GRT4EE4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2429be8c7081b91724d0af06ebabcddf4767907ac23b563d772b01cef51d095c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","title_canon_sha256":"996526acab70e8798028f0335d8b6418a80906240cecf5632d4bbf3337d22be0"},"schema_version":"1.0","source":{"id":"2309.08876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08876","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08876v2","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08876","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_12","alias_value":"CMLEP6DZY53X","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"CMLEP6DZY53XY3QC","created_at":"2026-07-05T07:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"CMLEP6DZ","created_at":"2026-07-05T07:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:f8930330ecc6e70fcabdf5a2df281255f39220140054c070c79738c46359b40d","target":"graph","created_at":"2026-07-05T07:31:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.08876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collecting audio-text pairs is expensive; however, it is much easier to access text-only data. Unless using shallow fusion, end-to-end automatic speech recognition (ASR) models require architecture modifications or additional training schemes to use text-only data. Inspired by recent advances in decoder-only language models (LMs), such as GPT-3 and PaLM adopted for speech-processing tasks, we propose using a decoder-only architecture for ASR with simple text augmentation. To provide audio information, encoder features compressed by CTC prediction are used as prompts for the decoder, which can ","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","title":"Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08876","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0903affa78e472763aed3713cf79eb05ac1d8a053f47d4d99e963b8c715b6971","target":"record","created_at":"2026-07-05T07:31:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2429be8c7081b91724d0af06ebabcddf4767907ac23b563d772b01cef51d095c","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-16T04:57:37Z","title_canon_sha256":"996526acab70e8798028f0335d8b6418a80906240cecf5632d4bbf3337d22be0"},"schema_version":"1.0","source":{"id":"2309.08876","kind":"arxiv","version":2}},"canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"131647f879c7777c6e0227f868cf84272b9cacb92bdd6a493955a22752137293","first_computed_at":"2026-07-05T07:31:31.949542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:31.949542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vk/a44iO4afC/jO4oVVEX3ODTDQI2vuIk+JUbRc9OOeylPDx4VUez9Htkb8+F9yvcVL15xKZOQ6tVVxAlQe7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:31.950083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0903affa78e472763aed3713cf79eb05ac1d8a053f47d4d99e963b8c715b6971","sha256:f8930330ecc6e70fcabdf5a2df281255f39220140054c070c79738c46359b40d"],"state_sha256":"ad53009295e23bfd9a0cac9c7ac1fa1afcbcedf1390665c81725e086d68dd127"}