{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AIQBJB56CDCPACUVRTW6DJ6WFS","short_pith_number":"pith:AIQBJB56","schema_version":"1.0","canonical_sha256":"02201487be10c4f00a958cede1a7d62c990a13f67124efabaa416142b2741ccd","source":{"kind":"arxiv","id":"2001.00577","version":1},"attestation_state":"computed","paper":{"title":"Attention based on-device streaming speech recognition with large speech corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chanwoo Kim, Daehyun Kim, Dhananjaya Gowda, Jinsu Yeo, Jungin Lee, Junmo Park, Kwangyoun Kim, Kyungmin Lee, Myoungji Han, Seokyeong Jung, Sichen Jin, Sungsoo Kim, Young-Yoon Lee","submitted_at":"2020-01-02T04:24:44Z","abstract_excerpt":"In this paper, we present a new on-device automatic speech recognition (ASR) system based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) corpus. We attained around 90% of a word recognition rate for general domain mainly by using joint training of connectionist temporal classifier (CTC) and cross entropy (CE) losses, minimum word error rate (MWER) training, layer-wise pre-training and data augmentation methods. In addition, we compressed our models by more than 3.4 times smaller using an iterative hyper low-rank approximation (LRA) method while minimizing the"},"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":"2001.00577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-02T04:24:44Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"003ba2be30274f62e7161bf84f91ab99af6da7d9e0ee6dc910f17ed88b524a86","abstract_canon_sha256":"34f6c4bb24a150c5bfd30e570bbeb9719604b4e265d0e34703f5a8090e619bbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:30.231690Z","signature_b64":"cE9l97YuMvuX0FMQynbDNnK37iFffHk1v/nKDfTxaolUIGGZG8twSktddzh1bxxyV34RD7+tqW1ANyaoB6epDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02201487be10c4f00a958cede1a7d62c990a13f67124efabaa416142b2741ccd","last_reissued_at":"2026-07-05T00:29:30.231341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:30.231341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention based on-device streaming speech recognition with large speech corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chanwoo Kim, Daehyun Kim, Dhananjaya Gowda, Jinsu Yeo, Jungin Lee, Junmo Park, Kwangyoun Kim, Kyungmin Lee, Myoungji Han, Seokyeong Jung, Sichen Jin, Sungsoo Kim, Young-Yoon Lee","submitted_at":"2020-01-02T04:24:44Z","abstract_excerpt":"In this paper, we present a new on-device automatic speech recognition (ASR) system based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) corpus. We attained around 90% of a word recognition rate for general domain mainly by using joint training of connectionist temporal classifier (CTC) and cross entropy (CE) losses, minimum word error rate (MWER) training, layer-wise pre-training and data augmentation methods. In addition, we compressed our models by more than 3.4 times smaller using an iterative hyper low-rank approximation (LRA) method while minimizing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00577","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.00577/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2001.00577","created_at":"2026-07-05T00:29:30.231404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00577v1","created_at":"2026-07-05T00:29:30.231404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00577","created_at":"2026-07-05T00:29:30.231404+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIQBJB56CDCP","created_at":"2026-07-05T00:29:30.231404+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIQBJB56CDCPACUV","created_at":"2026-07-05T00:29:30.231404+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIQBJB56","created_at":"2026-07-05T00:29:30.231404+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/AIQBJB56CDCPACUVRTW6DJ6WFS","json":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS.json","graph_json":"https://pith.science/api/pith-number/AIQBJB56CDCPACUVRTW6DJ6WFS/graph.json","events_json":"https://pith.science/api/pith-number/AIQBJB56CDCPACUVRTW6DJ6WFS/events.json","paper":"https://pith.science/paper/AIQBJB56"},"agent_actions":{"view_html":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS","download_json":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS.json","view_paper":"https://pith.science/paper/AIQBJB56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00577&json=true","fetch_graph":"https://pith.science/api/pith-number/AIQBJB56CDCPACUVRTW6DJ6WFS/graph.json","fetch_events":"https://pith.science/api/pith-number/AIQBJB56CDCPACUVRTW6DJ6WFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS/action/storage_attestation","attest_author":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS/action/author_attestation","sign_citation":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS/action/citation_signature","submit_replication":"https://pith.science/pith/AIQBJB56CDCPACUVRTW6DJ6WFS/action/replication_record"}},"created_at":"2026-07-05T00:29:30.231404+00:00","updated_at":"2026-07-05T00:29:30.231404+00:00"}