{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MAMMXVPVYRRFQAK5LTQBAYGUSF","short_pith_number":"pith:MAMMXVPV","canonical_record":{"source":{"id":"1606.05007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-15T23:45:33Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"f6d2cb093623d4f5ef5ec7e1dd35e2c70a65bd98b50b60100261bc4d73fd66d4","abstract_canon_sha256":"6731d0f0989e936091f8def26db02eccb64d97418d1cab66107806c383af137b"},"schema_version":"1.0"},"canonical_sha256":"6018cbd5f5c46258015d5ce01060d4915f76075a00de9f6c1d5085ee0f989929","source":{"kind":"arxiv","id":"1606.05007","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05007","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05007v1","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05007","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"MAMMXVPVYRRF","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MAMMXVPVYRRFQAK5","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MAMMXVPV","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MAMMXVPVYRRFQAK5LTQBAYGUSF","target":"record","payload":{"canonical_record":{"source":{"id":"1606.05007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-15T23:45:33Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"f6d2cb093623d4f5ef5ec7e1dd35e2c70a65bd98b50b60100261bc4d73fd66d4","abstract_canon_sha256":"6731d0f0989e936091f8def26db02eccb64d97418d1cab66107806c383af137b"},"schema_version":"1.0"},"canonical_sha256":"6018cbd5f5c46258015d5ce01060d4915f76075a00de9f6c1d5085ee0f989929","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:22.220557Z","signature_b64":"moMjpCYqRjWhYxBp9DddyBqnkwJWMPtvBF9uT/9Y1p7HAgvAYBkhdBKGOhZsfwbWyTOB2Y8Fas+DsdIJuwpuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6018cbd5f5c46258015d5ce01060d4915f76075a00de9f6c1d5085ee0f989929","last_reissued_at":"2026-05-18T01:12:22.220226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:22.220226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.05007","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iPIb4lcjtV39PC3MG3tIvtieFTRYN8Sv+njlGiIPizXfBN7TIqbO0fW9QDnZTf+1vaBiR2bjIPponp4DcXb2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:22:29.569753Z"},"content_sha256":"c072baeccec02a48575d3cafc4caca20ad310e615dcd4082a384a174bb6df01d","schema_version":"1.0","event_id":"sha256:c072baeccec02a48575d3cafc4caca20ad310e615dcd4082a384a174bb6df01d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MAMMXVPVYRRFQAK5LTQBAYGUSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Beat Pfister, Naoya Takahashi, Tofigh Naghibi","submitted_at":"2016-06-15T23:45:33Z","abstract_excerpt":"Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft a pronunciation dictionary, pronunciation variations, human mistakes and under-resourced dialects and languages. Here, we propose a data-driven pronunciation estimation and acoustic modeling method which only takes the orthographic transcription to jointly estimate a set of sub-word units and a reliable dictionary. Experimental results show that the proposed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05007","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3O+sUtSu+HR4K+SG1UA9lgTwRHcjOq0IlJ7wWvHwYbS2zHpfWEAXO1Xy0qvuC2l6sdRqoB3D88r5cNVhav3rAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:22:29.570096Z"},"content_sha256":"dcbbbd381565a9b8b275526101d08b861dc2ffc06a35682e8cbc81c60c2a1768","schema_version":"1.0","event_id":"sha256:dcbbbd381565a9b8b275526101d08b861dc2ffc06a35682e8cbc81c60c2a1768"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF/bundle.json","state_url":"https://pith.science/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T05:22:29Z","links":{"resolver":"https://pith.science/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF","bundle":"https://pith.science/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF/bundle.json","state":"https://pith.science/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAMMXVPVYRRFQAK5LTQBAYGUSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MAMMXVPVYRRFQAK5LTQBAYGUSF","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":"6731d0f0989e936091f8def26db02eccb64d97418d1cab66107806c383af137b","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-15T23:45:33Z","title_canon_sha256":"f6d2cb093623d4f5ef5ec7e1dd35e2c70a65bd98b50b60100261bc4d73fd66d4"},"schema_version":"1.0","source":{"id":"1606.05007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05007","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05007v1","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05007","created_at":"2026-05-18T01:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"MAMMXVPVYRRF","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MAMMXVPVYRRFQAK5","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MAMMXVPV","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:dcbbbd381565a9b8b275526101d08b861dc2ffc06a35682e8cbc81c60c2a1768","target":"graph","created_at":"2026-05-18T01:12:22Z","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"},"paper":{"abstract_excerpt":"Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft a pronunciation dictionary, pronunciation variations, human mistakes and under-resourced dialects and languages. Here, we propose a data-driven pronunciation estimation and acoustic modeling method which only takes the orthographic transcription to jointly estimate a set of sub-word units and a reliable dictionary. Experimental results show that the proposed","authors_text":"Beat Pfister, Naoya Takahashi, Tofigh Naghibi","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-15T23:45:33Z","title":"Automatic Pronunciation Generation by Utilizing a Semi-supervised Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05007","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:c072baeccec02a48575d3cafc4caca20ad310e615dcd4082a384a174bb6df01d","target":"record","created_at":"2026-05-18T01:12:22Z","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":"6731d0f0989e936091f8def26db02eccb64d97418d1cab66107806c383af137b","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-15T23:45:33Z","title_canon_sha256":"f6d2cb093623d4f5ef5ec7e1dd35e2c70a65bd98b50b60100261bc4d73fd66d4"},"schema_version":"1.0","source":{"id":"1606.05007","kind":"arxiv","version":1}},"canonical_sha256":"6018cbd5f5c46258015d5ce01060d4915f76075a00de9f6c1d5085ee0f989929","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6018cbd5f5c46258015d5ce01060d4915f76075a00de9f6c1d5085ee0f989929","first_computed_at":"2026-05-18T01:12:22.220226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:22.220226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"moMjpCYqRjWhYxBp9DddyBqnkwJWMPtvBF9uT/9Y1p7HAgvAYBkhdBKGOhZsfwbWyTOB2Y8Fas+DsdIJuwpuBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:22.220557Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.05007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c072baeccec02a48575d3cafc4caca20ad310e615dcd4082a384a174bb6df01d","sha256:dcbbbd381565a9b8b275526101d08b861dc2ffc06a35682e8cbc81c60c2a1768"],"state_sha256":"94b641e1a684d0f570f43d663ac5c0f3f11b714835df645e760f8946b27e578b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4EVEggAX9rxpd8ZQSdZdlmMMHkPrmx07x+4aZNKvmkDdKeLjUZwQUt4X9q5jWyJLOOKGMttIFtTvsYvNl2xAAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T05:22:29.573955Z","bundle_sha256":"df8c15c2ddbea7176580d57816086cb3d0b0f4a707d78dc825cc4ef2345d13e1"}}