{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:E6ZPR6NKISTSZ4HJ2VKLR2BM5A","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":"167e751986fb632d0f416dc1165af4a32a3da32895329e7f467e09738d34f7d3","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-10-22T21:49:50Z","title_canon_sha256":"d44695ab93f09b7bf62ddf0307a4cfea53da312f3cc84b9abe23045835430db3"},"schema_version":"1.0","source":{"id":"1910.12612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.12612","created_at":"2026-07-05T00:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"1910.12612v2","created_at":"2026-07-05T00:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12612","created_at":"2026-07-05T00:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"E6ZPR6NKISTS","created_at":"2026-07-05T00:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"E6ZPR6NKISTSZ4HJ","created_at":"2026-07-05T00:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"E6ZPR6NK","created_at":"2026-07-05T00:40:34Z"}],"graph_snapshots":[{"event_id":"sha256:dba42a1cdfcedcae075ed7d7e7f72d7e19e1a098be7050dfb41dd74774e44443","target":"graph","created_at":"2026-07-05T00:40:34Z","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/1910.12612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-based acoustic modeling has recently been shown to outperform phoneme-based approaches in both hybrid and end-to-end automatic speech recognition (ASR), even on non-phonemic languages like English. However, graphemic ASR still has problems with rare long-tail words that do not follow the standard spelling conventions seen in training, such as entity names. In this work, we present a novel method to train a statistical grapheme-to-grapheme (G2G) model on text-to-speech data that can rewrite an arbitrary character sequence into more phonetically consistent forms. We show that using G2G ","authors_text":"Christian Fuegen, Duc Le, Michael L. Seltzer, Thilo Koehler","cross_cats":["cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-10-22T21:49:50Z","title":"G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12612","kind":"arxiv","version":2},"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:f8f9b75229bc6f7956f5f18da80327f61ec61a078d9721899e4501f31e9c17ee","target":"record","created_at":"2026-07-05T00:40:34Z","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":"167e751986fb632d0f416dc1165af4a32a3da32895329e7f467e09738d34f7d3","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-10-22T21:49:50Z","title_canon_sha256":"d44695ab93f09b7bf62ddf0307a4cfea53da312f3cc84b9abe23045835430db3"},"schema_version":"1.0","source":{"id":"1910.12612","kind":"arxiv","version":2}},"canonical_sha256":"27b2f8f9aa44a72cf0e9d554b8e82ce8146feb37419fb92131be87c4cc8e90e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27b2f8f9aa44a72cf0e9d554b8e82ce8146feb37419fb92131be87c4cc8e90e9","first_computed_at":"2026-07-05T00:40:34.878381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:34.878381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vK+tgCGD25TXXynOVt7iIuNvKjT4Z14RH3U0abKHclv7WJWpc+/U+jJ7NJBmOuPP5+FD3jXqB3Ahvx94d/tUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:34.878799Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.12612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8f9b75229bc6f7956f5f18da80327f61ec61a078d9721899e4501f31e9c17ee","sha256:dba42a1cdfcedcae075ed7d7e7f72d7e19e1a098be7050dfb41dd74774e44443"],"state_sha256":"0bf5e76d84fa240e231a8543d221a4e1d26ee880077d00963f5e2d0f70960d2d"}