{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2KNTVW2SZFENQIKC7OB37VHFMS","short_pith_number":"pith:2KNTVW2S","schema_version":"1.0","canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","source":{"kind":"arxiv","id":"2407.04439","version":2},"attestation_state":"computed","paper":{"title":"XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Aravind Ganapathiraju, Esa\\'u Villatoro-Tello, Iuliia Thorbecke, Juan Zuluaga-Gomez, Manjunath K E, Petr Motlicek, Shashi Kumar, Srikanth Madikeri","submitted_at":"2024-07-05T11:41:11Z","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 "},"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":"2407.04439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169","abstract_canon_sha256":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:45.178573Z","signature_b64":"+eRWNgWvKlxPA1qcuginAzKCOtEEiQVPSadPWlB2RRV5R8ZKGe06md57+7SCcVRdeaNs5wypBKN5cYfy5YmOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","last_reissued_at":"2026-07-05T09:17:45.178095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:45.178095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Aravind Ganapathiraju, Esa\\'u Villatoro-Tello, Iuliia Thorbecke, Juan Zuluaga-Gomez, Manjunath K E, Petr Motlicek, Shashi Kumar, Srikanth Madikeri","submitted_at":"2024-07-05T11:41:11Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04439","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/2407.04439/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":"2407.04439","created_at":"2026-07-05T09:17:45.178156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04439v2","created_at":"2026-07-05T09:17:45.178156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04439","created_at":"2026-07-05T09:17:45.178156+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KNTVW2SZFEN","created_at":"2026-07-05T09:17:45.178156+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KNTVW2SZFENQIKC","created_at":"2026-07-05T09:17:45.178156+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KNTVW2S","created_at":"2026-07-05T09:17:45.178156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22487","citing_title":"Effective Context in Neural Speech Models","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS","json":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS.json","graph_json":"https://pith.science/api/pith-number/2KNTVW2SZFENQIKC7OB37VHFMS/graph.json","events_json":"https://pith.science/api/pith-number/2KNTVW2SZFENQIKC7OB37VHFMS/events.json","paper":"https://pith.science/paper/2KNTVW2S"},"agent_actions":{"view_html":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS","download_json":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS.json","view_paper":"https://pith.science/paper/2KNTVW2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04439&json=true","fetch_graph":"https://pith.science/api/pith-number/2KNTVW2SZFENQIKC7OB37VHFMS/graph.json","fetch_events":"https://pith.science/api/pith-number/2KNTVW2SZFENQIKC7OB37VHFMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/action/storage_attestation","attest_author":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/action/author_attestation","sign_citation":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/action/citation_signature","submit_replication":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/action/replication_record"}},"created_at":"2026-07-05T09:17:45.178156+00:00","updated_at":"2026-07-05T09:17:45.178156+00:00"}