{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KNTVW2SZFENQIKC7OB37VHFMS","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":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169"},"schema_version":"1.0","source":{"id":"2407.04439","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04439","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04439v2","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04439","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"2KNTVW2SZFEN","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"2KNTVW2SZFENQIKC","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"2KNTVW2S","created_at":"2026-07-05T09:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:b24645c19686921c13394283d64c611b6dbf25b2d3d07a9424c0e320168a7e77","target":"graph","created_at":"2026-07-05T09:17:45Z","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/2407.04439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are trained with full attention context. In this paper, we introduce XLSR-Transducer, where the XLSR-53 model is used as encoder in transducer setup. Our experiments on the AMI dataset reveal that the XLSR-Transducer achieves 4% absolute WER improvement over Whisper large-v2 and 8% over a Zipformer transducer model trained from scratch. To enable streaming ","authors_text":"Aravind Ganapathiraju, Esa\\'u Villatoro-Tello, Iuliia Thorbecke, Juan Zuluaga-Gomez, Manjunath K E, Petr Motlicek, Shashi Kumar, Srikanth Madikeri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","title":"XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04439","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":"sha256:9cf2b02ad6df569997246eac582e36d43f436517963ea3cd0cd6e1ff10382433","target":"record","created_at":"2026-07-05T09:17:45Z","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":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169"},"schema_version":"1.0","source":{"id":"2407.04439","kind":"arxiv","version":2}},"canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","first_computed_at":"2026-07-05T09:17:45.178095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:45.178095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+eRWNgWvKlxPA1qcuginAzKCOtEEiQVPSadPWlB2RRV5R8ZKGe06md57+7SCcVRdeaNs5wypBKN5cYfy5YmOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:45.178573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04439","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cf2b02ad6df569997246eac582e36d43f436517963ea3cd0cd6e1ff10382433","sha256:b24645c19686921c13394283d64c611b6dbf25b2d3d07a9424c0e320168a7e77"],"state_sha256":"2eb013742b7e0e0f8f575164b53c51b0344635139842b709dab736f460aedfde"}