{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A52WL46VMMYVFVY4B6DIL3MLZM","short_pith_number":"pith:A52WL46V","schema_version":"1.0","canonical_sha256":"077565f3d5633152d71c0f8685ed8bcb1fff5b632aa253a093368b635529f6c9","source":{"kind":"arxiv","id":"2209.06058","version":1},"attestation_state":"computed","paper":{"title":"Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Bo Li, Chao Zhang, Parisa Haghani, Sepand Mavandadi, Shuo-yiin Chang, Tara Sainath, Trevor Strohman","submitted_at":"2022-09-13T15:10:41Z","abstract_excerpt":"Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. B"},"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":"2209.06058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-13T15:10:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ce89dbe6ff1da86c3536ada81e1d39c341fe09291e59d40013739b8c3e15b121","abstract_canon_sha256":"cdd36395313a297c7b3f0bc61ac31e6671ebf3028885192fd9dbbb393bbc6dc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:19.569146Z","signature_b64":"/d0lQoMoztcH2iugIWI4E0GYH2h9eBY5L8JrEhdh3QxG9bJegigKlXPsj8jFBDpIHvU8kh7aJAbceEsu+QVqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"077565f3d5633152d71c0f8685ed8bcb1fff5b632aa253a093368b635529f6c9","last_reissued_at":"2026-07-05T04:57:19.568705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:19.568705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Bo Li, Chao Zhang, Parisa Haghani, Sepand Mavandadi, Shuo-yiin Chang, Tara Sainath, Trevor Strohman","submitted_at":"2022-09-13T15:10:41Z","abstract_excerpt":"Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06058","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/2209.06058/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":"2209.06058","created_at":"2026-07-05T04:57:19.568766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06058v1","created_at":"2026-07-05T04:57:19.568766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06058","created_at":"2026-07-05T04:57:19.568766+00:00"},{"alias_kind":"pith_short_12","alias_value":"A52WL46VMMYV","created_at":"2026-07-05T04:57:19.568766+00:00"},{"alias_kind":"pith_short_16","alias_value":"A52WL46VMMYVFVY4","created_at":"2026-07-05T04:57:19.568766+00:00"},{"alias_kind":"pith_short_8","alias_value":"A52WL46V","created_at":"2026-07-05T04:57:19.568766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05841","citing_title":"On the use of Performer and Agent Attention for Spoken Language Identification","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM","json":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM.json","graph_json":"https://pith.science/api/pith-number/A52WL46VMMYVFVY4B6DIL3MLZM/graph.json","events_json":"https://pith.science/api/pith-number/A52WL46VMMYVFVY4B6DIL3MLZM/events.json","paper":"https://pith.science/paper/A52WL46V"},"agent_actions":{"view_html":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM","download_json":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM.json","view_paper":"https://pith.science/paper/A52WL46V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06058&json=true","fetch_graph":"https://pith.science/api/pith-number/A52WL46VMMYVFVY4B6DIL3MLZM/graph.json","fetch_events":"https://pith.science/api/pith-number/A52WL46VMMYVFVY4B6DIL3MLZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM/action/storage_attestation","attest_author":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM/action/author_attestation","sign_citation":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM/action/citation_signature","submit_replication":"https://pith.science/pith/A52WL46VMMYVFVY4B6DIL3MLZM/action/replication_record"}},"created_at":"2026-07-05T04:57:19.568766+00:00","updated_at":"2026-07-05T04:57:19.568766+00:00"}