{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A52WL46VMMYVFVY4B6DIL3MLZM","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":"cdd36395313a297c7b3f0bc61ac31e6671ebf3028885192fd9dbbb393bbc6dc9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-13T15:10:41Z","title_canon_sha256":"ce89dbe6ff1da86c3536ada81e1d39c341fe09291e59d40013739b8c3e15b121"},"schema_version":"1.0","source":{"id":"2209.06058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06058","created_at":"2026-07-05T04:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06058v1","created_at":"2026-07-05T04:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06058","created_at":"2026-07-05T04:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"A52WL46VMMYV","created_at":"2026-07-05T04:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"A52WL46VMMYVFVY4","created_at":"2026-07-05T04:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"A52WL46V","created_at":"2026-07-05T04:57:19Z"}],"graph_snapshots":[{"event_id":"sha256:11dae0de841eeb9d66489afd4357f4192c57dab9195dd16274f10945be6121ee","target":"graph","created_at":"2026-07-05T04:57:19Z","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/2209.06058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Li, Chao Zhang, Parisa Haghani, Sepand Mavandadi, Shuo-yiin Chang, Tara Sainath, Trevor Strohman","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-13T15:10:41Z","title":"Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06058","kind":"arxiv","version":1},"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":"sha256:2cf0d447e9c25e0ee0e5f34112f98606280cf8ef7f12ebca8e4fe120a1513697","target":"record","created_at":"2026-07-05T04:57:19Z","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":"cdd36395313a297c7b3f0bc61ac31e6671ebf3028885192fd9dbbb393bbc6dc9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-13T15:10:41Z","title_canon_sha256":"ce89dbe6ff1da86c3536ada81e1d39c341fe09291e59d40013739b8c3e15b121"},"schema_version":"1.0","source":{"id":"2209.06058","kind":"arxiv","version":1}},"canonical_sha256":"077565f3d5633152d71c0f8685ed8bcb1fff5b632aa253a093368b635529f6c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"077565f3d5633152d71c0f8685ed8bcb1fff5b632aa253a093368b635529f6c9","first_computed_at":"2026-07-05T04:57:19.568705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:19.568705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/d0lQoMoztcH2iugIWI4E0GYH2h9eBY5L8JrEhdh3QxG9bJegigKlXPsj8jFBDpIHvU8kh7aJAbceEsu+QVqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:19.569146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cf0d447e9c25e0ee0e5f34112f98606280cf8ef7f12ebca8e4fe120a1513697","sha256:11dae0de841eeb9d66489afd4357f4192c57dab9195dd16274f10945be6121ee"],"state_sha256":"e730f202bc0506713fe6b4d6a6a252995a6198fcaf48e5b45749ee7549abba91"}