{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JY2HNHE6DB6TQOR3VFRHEEAYRQ","short_pith_number":"pith:JY2HNHE6","schema_version":"1.0","canonical_sha256":"4e34769c9e187d383a3ba9627210188c006aab5567816faf5d01dd93f8bd5956","source":{"kind":"arxiv","id":"2406.18862","version":1},"attestation_state":"computed","paper":{"title":"Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Changhao Shan, Lei Xie, Peikun Chen, Qing Yang, Sining Sun","submitted_at":"2024-06-27T03:16:22Z","abstract_excerpt":"Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (ASR). These models typically adopt a unified method to model discrete speech and text tokens, followed by training a decoder-only transformer. However, they are all designed for non-streaming ASR tasks, where the entire speech utterance is needed during decoding. Hence, we introduce a decoder-only model exclusively designed for streaming recognition, incorporating a dedicated boundary token to facilitate streaming rec"},"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":"2406.18862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-27T03:16:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c2e8d2ed1fcfd771ad46a9d5a7c5633a4a58a42c05547595ca972eddb485c5d3","abstract_canon_sha256":"876ba734eb7c62470bb98113ab3690dc820f052504ee5c2c68d71753ed541492"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:26.800506Z","signature_b64":"hX2G7Xsq6bN/A4yeKNn6mSO+KmleziS6MDeQ8O7OSapyItxlaK9jGrvhcEK7jI/yBiIrbAkO/vHHX7OWSddRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e34769c9e187d383a3ba9627210188c006aab5567816faf5d01dd93f8bd5956","last_reissued_at":"2026-07-05T08:37:26.800134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:26.800134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Changhao Shan, Lei Xie, Peikun Chen, Qing Yang, Sining Sun","submitted_at":"2024-06-27T03:16:22Z","abstract_excerpt":"Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (ASR). These models typically adopt a unified method to model discrete speech and text tokens, followed by training a decoder-only transformer. However, they are all designed for non-streaming ASR tasks, where the entire speech utterance is needed during decoding. Hence, we introduce a decoder-only model exclusively designed for streaming recognition, incorporating a dedicated boundary token to facilitate streaming rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18862","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/2406.18862/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":"2406.18862","created_at":"2026-07-05T08:37:26.800191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18862v1","created_at":"2026-07-05T08:37:26.800191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18862","created_at":"2026-07-05T08:37:26.800191+00:00"},{"alias_kind":"pith_short_12","alias_value":"JY2HNHE6DB6T","created_at":"2026-07-05T08:37:26.800191+00:00"},{"alias_kind":"pith_short_16","alias_value":"JY2HNHE6DB6TQOR3","created_at":"2026-07-05T08:37:26.800191+00:00"},{"alias_kind":"pith_short_8","alias_value":"JY2HNHE6","created_at":"2026-07-05T08:37:26.800191+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/JY2HNHE6DB6TQOR3VFRHEEAYRQ","json":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ.json","graph_json":"https://pith.science/api/pith-number/JY2HNHE6DB6TQOR3VFRHEEAYRQ/graph.json","events_json":"https://pith.science/api/pith-number/JY2HNHE6DB6TQOR3VFRHEEAYRQ/events.json","paper":"https://pith.science/paper/JY2HNHE6"},"agent_actions":{"view_html":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ","download_json":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ.json","view_paper":"https://pith.science/paper/JY2HNHE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18862&json=true","fetch_graph":"https://pith.science/api/pith-number/JY2HNHE6DB6TQOR3VFRHEEAYRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JY2HNHE6DB6TQOR3VFRHEEAYRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ/action/storage_attestation","attest_author":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ/action/author_attestation","sign_citation":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ/action/citation_signature","submit_replication":"https://pith.science/pith/JY2HNHE6DB6TQOR3VFRHEEAYRQ/action/replication_record"}},"created_at":"2026-07-05T08:37:26.800191+00:00","updated_at":"2026-07-05T08:37:26.800191+00:00"}