{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VX2LH7TQP2HN5J35HCPSDMU2DC","short_pith_number":"pith:VX2LH7TQ","schema_version":"1.0","canonical_sha256":"adf4b3fe707e8edea77d389f21b29a18953c462b2becad649588beb3ea80d709","source":{"kind":"arxiv","id":"1811.06621","version":1},"attestation_state":"computed","paper":{"title":"Streaming End-to-end Speech Recognition For Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Gruenstein, Anjuli Kannan, Bo Li, David Rybach, Deepti Bhatia, Ding Zhao, Golan Pundak, Ian McGraw, Kanishka Rao, Khe Chai Sim, Qiao Liang, Raziel Alvarez, Rohit Prabhavalkar, Ruoming Pang, Shuo-yiin Chang, Tara N. Sainath, Tom Bagby, Yanzhang He, Yonghui Wu, Yuan Shangguan","submitted_at":"2018-11-15T23:09:44Z","abstract_excerpt":"End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use cases; they must be able to leverage user-specific context (e.g., contact lists); and above all, they must be extremely accurate. In this work, we describe our efforts at building an E2E speech recognizer using a recurrent neural network transducer"},"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":"1811.06621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-15T23:09:44Z","cross_cats_sorted":[],"title_canon_sha256":"c2797030fc8a483dff7ab9ee5f7ed98fa5ecc35708b15fba56d9c33645a3d181","abstract_canon_sha256":"3f60022cf68c3550b54a969110ec45c5867cd2392c2a78a753c576e30404a64c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:34.349693Z","signature_b64":"/WLKLG+uVl4+sdlmH9Av5tI7AfHN1Mt5u66BCDsjlnH3BsZDCky0YMJeP+UDXfcqLLydwCOxweSIToT+TDsXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adf4b3fe707e8edea77d389f21b29a18953c462b2becad649588beb3ea80d709","last_reissued_at":"2026-05-18T00:00:34.349094Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:34.349094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming End-to-end Speech Recognition For Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Gruenstein, Anjuli Kannan, Bo Li, David Rybach, Deepti Bhatia, Ding Zhao, Golan Pundak, Ian McGraw, Kanishka Rao, Khe Chai Sim, Qiao Liang, Raziel Alvarez, Rohit Prabhavalkar, Ruoming Pang, Shuo-yiin Chang, Tara N. Sainath, Tom Bagby, Yanzhang He, Yonghui Wu, Yuan Shangguan","submitted_at":"2018-11-15T23:09:44Z","abstract_excerpt":"End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use cases; they must be able to leverage user-specific context (e.g., contact lists); and above all, they must be extremely accurate. In this work, we describe our efforts at building an E2E speech recognizer using a recurrent neural network transducer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06621","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":"1811.06621","created_at":"2026-05-18T00:00:34.349202+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.06621v1","created_at":"2026-05-18T00:00:34.349202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06621","created_at":"2026-05-18T00:00:34.349202+00:00"},{"alias_kind":"pith_short_12","alias_value":"VX2LH7TQP2HN","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VX2LH7TQP2HN5J35","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VX2LH7TQ","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09292","citing_title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01372","citing_title":"Improving Performance of End-to-End ASR on Numeric Sequences","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05337","citing_title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC","json":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC.json","graph_json":"https://pith.science/api/pith-number/VX2LH7TQP2HN5J35HCPSDMU2DC/graph.json","events_json":"https://pith.science/api/pith-number/VX2LH7TQP2HN5J35HCPSDMU2DC/events.json","paper":"https://pith.science/paper/VX2LH7TQ"},"agent_actions":{"view_html":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC","download_json":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC.json","view_paper":"https://pith.science/paper/VX2LH7TQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.06621&json=true","fetch_graph":"https://pith.science/api/pith-number/VX2LH7TQP2HN5J35HCPSDMU2DC/graph.json","fetch_events":"https://pith.science/api/pith-number/VX2LH7TQP2HN5J35HCPSDMU2DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC/action/storage_attestation","attest_author":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC/action/author_attestation","sign_citation":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC/action/citation_signature","submit_replication":"https://pith.science/pith/VX2LH7TQP2HN5J35HCPSDMU2DC/action/replication_record"}},"created_at":"2026-05-18T00:00:34.349202+00:00","updated_at":"2026-05-18T00:00:34.349202+00:00"}