{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:I56ZM6ZHKM2XP2YUJDDDHVCKMS","short_pith_number":"pith:I56ZM6ZH","schema_version":"1.0","canonical_sha256":"477d967b27533577eb1448c633d44a6484cad9efe8750241696afeee474b15b5","source":{"kind":"arxiv","id":"1610.09975","version":1},"attestation_state":"computed","paper":{"title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hagen Soltau, Hank Liao, Hasim Sak","submitted_at":"2016-10-31T15:36:42Z","abstract_excerpt":"We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly using deep bi-directional LSTM RNNs with CTC loss. The model is trained on 125,000 hours of semi-supervised acoustic training data, which enables us to alleviate the data sparsity problem for word models. We show that the CTC word models work very well as an end-to-end all-neural speech recognition model without the use of traditional context-dependent sub-"},"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":"1610.09975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T15:36:42Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"5eb0a31a5279485a898387c9cca6caa38ac686f8301b9c8bb25492e55275bade","abstract_canon_sha256":"ff02ff58a6987a4bf5b4b85566108a21c6bc174572527a0a27c8973d6196001d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:46.818279Z","signature_b64":"ujam++FmtxUbpCEH4PiqIEs6caGwoxTtqaYmLqVAA613yGtrtt9hPQl3Wvpx52FphGj9Zfk49fni9Xg1nzVCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"477d967b27533577eb1448c633d44a6484cad9efe8750241696afeee474b15b5","last_reissued_at":"2026-05-18T01:00:46.817915Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:46.817915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Hagen Soltau, Hank Liao, Hasim Sak","submitted_at":"2016-10-31T15:36:42Z","abstract_excerpt":"We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly using deep bi-directional LSTM RNNs with CTC loss. The model is trained on 125,000 hours of semi-supervised acoustic training data, which enables us to alleviate the data sparsity problem for word models. We show that the CTC word models work very well as an end-to-end all-neural speech recognition model without the use of traditional context-dependent sub-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09975","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":"1610.09975","created_at":"2026-05-18T01:00:46.817970+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.09975v1","created_at":"2026-05-18T01:00:46.817970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09975","created_at":"2026-05-18T01:00:46.817970+00:00"},{"alias_kind":"pith_short_12","alias_value":"I56ZM6ZHKM2X","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"I56ZM6ZHKM2XP2YU","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"I56ZM6ZH","created_at":"2026-05-18T12:30:22.444734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09292","citing_title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"1906.12170","citing_title":"LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS","json":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS.json","graph_json":"https://pith.science/api/pith-number/I56ZM6ZHKM2XP2YUJDDDHVCKMS/graph.json","events_json":"https://pith.science/api/pith-number/I56ZM6ZHKM2XP2YUJDDDHVCKMS/events.json","paper":"https://pith.science/paper/I56ZM6ZH"},"agent_actions":{"view_html":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS","download_json":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS.json","view_paper":"https://pith.science/paper/I56ZM6ZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.09975&json=true","fetch_graph":"https://pith.science/api/pith-number/I56ZM6ZHKM2XP2YUJDDDHVCKMS/graph.json","fetch_events":"https://pith.science/api/pith-number/I56ZM6ZHKM2XP2YUJDDDHVCKMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS/action/storage_attestation","attest_author":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS/action/author_attestation","sign_citation":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS/action/citation_signature","submit_replication":"https://pith.science/pith/I56ZM6ZHKM2XP2YUJDDDHVCKMS/action/replication_record"}},"created_at":"2026-05-18T01:00:46.817970+00:00","updated_at":"2026-05-18T01:00:46.817970+00:00"}