{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A73MXEHCIR424CXRMCQKZR2RKA","short_pith_number":"pith:A73MXEHC","schema_version":"1.0","canonical_sha256":"07f6cb90e24479ae0af160a0acc751501241ea528b49c2759885f79d4962ccd7","source":{"kind":"arxiv","id":"2406.16107","version":2},"attestation_state":"computed","paper":{"title":"Decoder-only Architecture for Streaming End-to-end Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2024-06-23T13:50:08Z","abstract_excerpt":"Decoder-only language models (LMs) have been successfully adopted for speech-processing tasks including automatic speech recognition (ASR). The LMs have ample expressiveness and perform efficiently. This efficiency is a suitable characteristic for streaming applications of ASR. In this work, we propose to use a decoder-only architecture for blockwise streaming ASR. In our approach, speech features are compressed using CTC output and context embedding using blockwise speech subnetwork, and are sequentially provided as prompts to the decoder. The decoder estimates the output tokens promptly at e"},"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":"2406.16107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-23T13:50:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"414471dd2e3834dc961a77278e6ec3f78196b519a0f6dfd82a8a026b4c5f1654","abstract_canon_sha256":"e554b4757ff20ea3babef5e6acfc2bcadf7f7fcaa12ad22f8453ed837af2e08d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:57.223410Z","signature_b64":"0wkaJ6DS26k4lYQd/C5XLmstt+YaFBZ8rC/cXSygyDiYBh/fqgIfkBB6HjVMEKP205gVR8ljUUtiZO4AH/YgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07f6cb90e24479ae0af160a0acc751501241ea528b49c2759885f79d4962ccd7","last_reissued_at":"2026-07-05T08:50:57.222991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:57.222991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoder-only Architecture for Streaming End-to-end Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2024-06-23T13:50:08Z","abstract_excerpt":"Decoder-only language models (LMs) have been successfully adopted for speech-processing tasks including automatic speech recognition (ASR). The LMs have ample expressiveness and perform efficiently. This efficiency is a suitable characteristic for streaming applications of ASR. In this work, we propose to use a decoder-only architecture for blockwise streaming ASR. In our approach, speech features are compressed using CTC output and context embedding using blockwise speech subnetwork, and are sequentially provided as prompts to the decoder. The decoder estimates the output tokens promptly at e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16107","kind":"arxiv","version":2},"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/2406.16107/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":"2406.16107","created_at":"2026-07-05T08:50:57.223044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16107v2","created_at":"2026-07-05T08:50:57.223044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16107","created_at":"2026-07-05T08:50:57.223044+00:00"},{"alias_kind":"pith_short_12","alias_value":"A73MXEHCIR42","created_at":"2026-07-05T08:50:57.223044+00:00"},{"alias_kind":"pith_short_16","alias_value":"A73MXEHCIR424CXR","created_at":"2026-07-05T08:50:57.223044+00:00"},{"alias_kind":"pith_short_8","alias_value":"A73MXEHC","created_at":"2026-07-05T08:50:57.223044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03722","citing_title":"MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA","json":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA.json","graph_json":"https://pith.science/api/pith-number/A73MXEHCIR424CXRMCQKZR2RKA/graph.json","events_json":"https://pith.science/api/pith-number/A73MXEHCIR424CXRMCQKZR2RKA/events.json","paper":"https://pith.science/paper/A73MXEHC"},"agent_actions":{"view_html":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA","download_json":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA.json","view_paper":"https://pith.science/paper/A73MXEHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16107&json=true","fetch_graph":"https://pith.science/api/pith-number/A73MXEHCIR424CXRMCQKZR2RKA/graph.json","fetch_events":"https://pith.science/api/pith-number/A73MXEHCIR424CXRMCQKZR2RKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA/action/storage_attestation","attest_author":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA/action/author_attestation","sign_citation":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA/action/citation_signature","submit_replication":"https://pith.science/pith/A73MXEHCIR424CXRMCQKZR2RKA/action/replication_record"}},"created_at":"2026-07-05T08:50:57.223044+00:00","updated_at":"2026-07-05T08:50:57.223044+00:00"}