{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JPWIWD7VFA2UQXMFBDRRWDQNAA","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":"23f9388de2208a0b5eb968678f5d74e4ec3ed1e634a5acfb67d450ef4d6021f1","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T20:37:03Z","title_canon_sha256":"5d981dba03b6b1ecf5ade625e0d79020127a617592f99d061b53f459cc47dea8"},"schema_version":"1.0","source":{"id":"2112.05820","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05820","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05820v3","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05820","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"JPWIWD7VFA2U","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"JPWIWD7VFA2UQXMF","created_at":"2026-07-05T03:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"JPWIWD7V","created_at":"2026-07-05T03:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:65f64ce5945f04e8e418253db91c1feec464d4782fe83fd4dae25346a4de94e2","target":"graph","created_at":"2026-07-05T03:45:12Z","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/2112.05820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The sparsely-gated Mixture of Experts (MoE) can magnify a network capacity with a little computational complexity. In this work, we investigate how multi-lingual Automatic Speech Recognition (ASR) networks can be scaled up with a simple routing algorithm in order to achieve better accuracy. More specifically, we apply the sparsely-gated MoE technique to two types of networks: Sequence-to-Sequence Transformer (S2S-T) and Transformer Transducer (T-T). We demonstrate through a set of ASR experiments on multiple language data that the MoE networks can reduce the relative word error rates by 16.3% ","authors_text":"Devang Patel, Eric Sun, Felipe Cruz Salinas, Kenichi Kumatani, Linquan Liu, Robert Gmyr, Wei Zuo, Yu Shi","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T20:37:03Z","title":"Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05820","kind":"arxiv","version":3},"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":"sha256:90cd469a5bab9fafd23010628bb5763cb473d6d0e45fc918cdf10277e3673664","target":"record","created_at":"2026-07-05T03:45:12Z","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":"23f9388de2208a0b5eb968678f5d74e4ec3ed1e634a5acfb67d450ef4d6021f1","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T20:37:03Z","title_canon_sha256":"5d981dba03b6b1ecf5ade625e0d79020127a617592f99d061b53f459cc47dea8"},"schema_version":"1.0","source":{"id":"2112.05820","kind":"arxiv","version":3}},"canonical_sha256":"4bec8b0ff52835485d8508e31b0e0d001f30651a3b6bede22ce259be5b44e0e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bec8b0ff52835485d8508e31b0e0d001f30651a3b6bede22ce259be5b44e0e7","first_computed_at":"2026-07-05T03:45:12.697120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:12.697120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ESm0oPj30Jb1IkUcB1qfsNyTAn7lFjSTnTv8mee/BeqWdkxx0PZxg4iBNxLmRzM8opB41h9hH4LfjABOooyDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:12.697609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05820","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90cd469a5bab9fafd23010628bb5763cb473d6d0e45fc918cdf10277e3673664","sha256:65f64ce5945f04e8e418253db91c1feec464d4782fe83fd4dae25346a4de94e2"],"state_sha256":"58858d6b841b016949bbdbbc590e68c0d20265966fffbcaaed61d7591402cbaa"}