{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KCVTCB3KKFLEEBOYRC5PHMEIMV","short_pith_number":"pith:KCVTCB3K","schema_version":"1.0","canonical_sha256":"50ab31076a51564205d888baf3b0886563caf6b471f9af8722862b1bef97dae4","source":{"kind":"arxiv","id":"1812.09323","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Chengzhu Yu, Chih-Kuan Yeh, Dong Yu, Jianshu Chen","submitted_at":"2018-12-23T01:58:39Z","abstract_excerpt":"We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between solving two sub-problems: (i) learn a phoneme classifier for a given set of phoneme segmentation boundaries, and (ii) refining the phoneme boundaries based on a given classifier. To solve the first sub-problem, we introduce a novel unsupervised cost function named Segmental Empiric"},"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":"1812.09323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-12-23T01:58:39Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"8fc819b2f101fef5dad4401ffd79b63d6cde30cae56a1b93c4d1ec88b9979e38","abstract_canon_sha256":"968cb6ddd0870d35b93eff86e79a501a50a1da9814d3c917147673316b29edba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:30.364697Z","signature_b64":"QZkrXLMXDJeFSMYDaya5UfoSAauGcN+sqPniW2YDfvYIbyBtfXou3GiGLinAMbTs8gEItExi0mfGohcNpxdrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50ab31076a51564205d888baf3b0886563caf6b471f9af8722862b1bef97dae4","last_reissued_at":"2026-05-17T23:57:30.364081Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:30.364081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Chengzhu Yu, Chih-Kuan Yeh, Dong Yu, Jianshu Chen","submitted_at":"2018-12-23T01:58:39Z","abstract_excerpt":"We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between solving two sub-problems: (i) learn a phoneme classifier for a given set of phoneme segmentation boundaries, and (ii) refining the phoneme boundaries based on a given classifier. To solve the first sub-problem, we introduce a novel unsupervised cost function named Segmental Empiric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09323","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":""},"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":"1812.09323","created_at":"2026-05-17T23:57:30.364167+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09323v1","created_at":"2026-05-17T23:57:30.364167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09323","created_at":"2026-05-17T23:57:30.364167+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCVTCB3KKFLE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCVTCB3KKFLEEBOY","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCVTCB3K","created_at":"2026-05-18T12:32:33.847187+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/KCVTCB3KKFLEEBOYRC5PHMEIMV","json":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV.json","graph_json":"https://pith.science/api/pith-number/KCVTCB3KKFLEEBOYRC5PHMEIMV/graph.json","events_json":"https://pith.science/api/pith-number/KCVTCB3KKFLEEBOYRC5PHMEIMV/events.json","paper":"https://pith.science/paper/KCVTCB3K"},"agent_actions":{"view_html":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV","download_json":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV.json","view_paper":"https://pith.science/paper/KCVTCB3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09323&json=true","fetch_graph":"https://pith.science/api/pith-number/KCVTCB3KKFLEEBOYRC5PHMEIMV/graph.json","fetch_events":"https://pith.science/api/pith-number/KCVTCB3KKFLEEBOYRC5PHMEIMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV/action/storage_attestation","attest_author":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV/action/author_attestation","sign_citation":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV/action/citation_signature","submit_replication":"https://pith.science/pith/KCVTCB3KKFLEEBOYRC5PHMEIMV/action/replication_record"}},"created_at":"2026-05-17T23:57:30.364167+00:00","updated_at":"2026-05-17T23:57:30.364167+00:00"}