{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AEOHLWMVULD2VJF3CAU5PE6GI3","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":"8b87f77e2d566aaeac1013fe17675f79f29907ba689b28d4b5226e9b82c2b791","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-06T22:48:29Z","title_canon_sha256":"0604128e6681a394ddc378e3af46861c1bc8ca964d00b61cb85944cb0e69449e"},"schema_version":"1.0","source":{"id":"2209.02842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.02842","created_at":"2026-07-05T04:55:20Z"},{"alias_kind":"arxiv_version","alias_value":"2209.02842v1","created_at":"2026-07-05T04:55:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.02842","created_at":"2026-07-05T04:55:20Z"},{"alias_kind":"pith_short_12","alias_value":"AEOHLWMVULD2","created_at":"2026-07-05T04:55:20Z"},{"alias_kind":"pith_short_16","alias_value":"AEOHLWMVULD2VJF3","created_at":"2026-07-05T04:55:20Z"},{"alias_kind":"pith_short_8","alias_value":"AEOHLWMV","created_at":"2026-07-05T04:55:20Z"}],"graph_snapshots":[{"event_id":"sha256:0e577dbe61cd302684023281c5847730d38bf7e6de533adc17956081f85bba63","target":"graph","created_at":"2026-07-05T04:55:20Z","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/2209.02842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most recent speech recognition models rely on large supervised datasets, which are unavailable for many low-resource languages. In this work, we present a speech recognition pipeline that does not require any audio for the target language. The only assumption is that we have access to raw text datasets or a set of n-gram statistics. Our speech pipeline consists of three components: acoustic, pronunciation, and language models. Unlike the standard pipeline, our acoustic and pronunciation models use multilingual models without any supervision. The language model is built using n-gram statistics ","authors_text":"Alan W Black, David R Mortensen, Florian Metze, Shinji Watanabe, Xinjian Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-06T22:48:29Z","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.02842","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":"sha256:330e062065a757abed9bb15916690d1c17106f34f7ad2ebb5b249e0642b434ab","target":"record","created_at":"2026-07-05T04:55:20Z","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":"8b87f77e2d566aaeac1013fe17675f79f29907ba689b28d4b5226e9b82c2b791","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-06T22:48:29Z","title_canon_sha256":"0604128e6681a394ddc378e3af46861c1bc8ca964d00b61cb85944cb0e69449e"},"schema_version":"1.0","source":{"id":"2209.02842","kind":"arxiv","version":1}},"canonical_sha256":"011c75d995a2c7aaa4bb1029d793c646c77f81503f84ac92288d3340b6fa1242","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"011c75d995a2c7aaa4bb1029d793c646c77f81503f84ac92288d3340b6fa1242","first_computed_at":"2026-07-05T04:55:20.459943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:55:20.459943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aukFlOEfrBuY9sTfXPEMgTsNspJ1emgWg4QzLjQZn9Y/+xU0hbNDoU6YCQOneFB2p9bRQPUFLsVfb0Yo1xGhCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:55:20.460350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.02842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:330e062065a757abed9bb15916690d1c17106f34f7ad2ebb5b249e0642b434ab","sha256:0e577dbe61cd302684023281c5847730d38bf7e6de533adc17956081f85bba63"],"state_sha256":"f6d5dc66f648b8ea075776ead673b8b31ac7ac09c5525decc63dce1d116758f4"}