{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AEOHLWMVULD2VJF3CAU5PE6GI3","short_pith_number":"pith:AEOHLWMV","schema_version":"1.0","canonical_sha256":"011c75d995a2c7aaa4bb1029d793c646c77f81503f84ac92288d3340b6fa1242","source":{"kind":"arxiv","id":"2209.02842","version":1},"attestation_state":"computed","paper":{"title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, David R Mortensen, Florian Metze, Shinji Watanabe, Xinjian Li","submitted_at":"2022-09-06T22:48:29Z","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 "},"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":"2209.02842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-06T22:48:29Z","cross_cats_sorted":[],"title_canon_sha256":"0604128e6681a394ddc378e3af46861c1bc8ca964d00b61cb85944cb0e69449e","abstract_canon_sha256":"8b87f77e2d566aaeac1013fe17675f79f29907ba689b28d4b5226e9b82c2b791"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:20.460350Z","signature_b64":"aukFlOEfrBuY9sTfXPEMgTsNspJ1emgWg4QzLjQZn9Y/+xU0hbNDoU6YCQOneFB2p9bRQPUFLsVfb0Yo1xGhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"011c75d995a2c7aaa4bb1029d793c646c77f81503f84ac92288d3340b6fa1242","last_reissued_at":"2026-07-05T04:55:20.459943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:20.459943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, David R Mortensen, Florian Metze, Shinji Watanabe, Xinjian Li","submitted_at":"2022-09-06T22:48:29Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.02842","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/2209.02842/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":"2209.02842","created_at":"2026-07-05T04:55:20.460003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.02842v1","created_at":"2026-07-05T04:55:20.460003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.02842","created_at":"2026-07-05T04:55:20.460003+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEOHLWMVULD2","created_at":"2026-07-05T04:55:20.460003+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEOHLWMVULD2VJF3","created_at":"2026-07-05T04:55:20.460003+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEOHLWMV","created_at":"2026-07-05T04:55:20.460003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3","json":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3.json","graph_json":"https://pith.science/api/pith-number/AEOHLWMVULD2VJF3CAU5PE6GI3/graph.json","events_json":"https://pith.science/api/pith-number/AEOHLWMVULD2VJF3CAU5PE6GI3/events.json","paper":"https://pith.science/paper/AEOHLWMV"},"agent_actions":{"view_html":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3","download_json":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3.json","view_paper":"https://pith.science/paper/AEOHLWMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.02842&json=true","fetch_graph":"https://pith.science/api/pith-number/AEOHLWMVULD2VJF3CAU5PE6GI3/graph.json","fetch_events":"https://pith.science/api/pith-number/AEOHLWMVULD2VJF3CAU5PE6GI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3/action/storage_attestation","attest_author":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3/action/author_attestation","sign_citation":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3/action/citation_signature","submit_replication":"https://pith.science/pith/AEOHLWMVULD2VJF3CAU5PE6GI3/action/replication_record"}},"created_at":"2026-07-05T04:55:20.460003+00:00","updated_at":"2026-07-05T04:55:20.460003+00:00"}