{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RYCK2LVMHMY6XUNEIZ5Y3FT42N","short_pith_number":"pith:RYCK2LVM","schema_version":"1.0","canonical_sha256":"8e04ad2eac3b31ebd1a4467b8d967cd34e95480cb082f891292b5dd926fb9635","source":{"kind":"arxiv","id":"2006.10407","version":2},"attestation_state":"computed","paper":{"title":"Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emre Y{\\i}lmaz, Grandee Lee, Haizhou Li, Jiaen Liang, Xinyuan Zhou, Yanhua Long","submitted_at":"2020-06-18T10:24:18Z","abstract_excerpt":"The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding of the target outputs. In this paper, we propose a novel decoder structure that features a self-and-mixed attention decoder (SMAD) with a deep acoustic structure (DAS) to improve the acoustic representation of Transformer-based LVCSR. Specifically, we introduce a self-attention mechanism to learn a multi-layer deep acoustic structure for multiple levels of ac"},"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":"2006.10407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-18T10:24:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ed93fefbda11d4405554cbac20e9fd880b5750cbc9a2ad1b8732de43d1d8618c","abstract_canon_sha256":"d44f204326bb0804de3ae73ea205475a3d87ff3881c613ce7fd329acf983171c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:34.019092Z","signature_b64":"wN9ADgkXMjvApybSprmx44ZASzCzmSR73q0eRlcar0OI4eaGqjn/0LLg3JlzMEwu4fwf3sD6X0MDE5+CHm8LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e04ad2eac3b31ebd1a4467b8d967cd34e95480cb082f891292b5dd926fb9635","last_reissued_at":"2026-07-05T01:35:34.018598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:34.018598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emre Y{\\i}lmaz, Grandee Lee, Haizhou Li, Jiaen Liang, Xinyuan Zhou, Yanhua Long","submitted_at":"2020-06-18T10:24:18Z","abstract_excerpt":"The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding of the target outputs. In this paper, we propose a novel decoder structure that features a self-and-mixed attention decoder (SMAD) with a deep acoustic structure (DAS) to improve the acoustic representation of Transformer-based LVCSR. Specifically, we introduce a self-attention mechanism to learn a multi-layer deep acoustic structure for multiple levels of ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10407","kind":"arxiv","version":2},"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/2006.10407/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":"2006.10407","created_at":"2026-07-05T01:35:34.018664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10407v2","created_at":"2026-07-05T01:35:34.018664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10407","created_at":"2026-07-05T01:35:34.018664+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYCK2LVMHMY6","created_at":"2026-07-05T01:35:34.018664+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYCK2LVMHMY6XUNE","created_at":"2026-07-05T01:35:34.018664+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYCK2LVM","created_at":"2026-07-05T01:35:34.018664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09535","citing_title":"Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N","json":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N.json","graph_json":"https://pith.science/api/pith-number/RYCK2LVMHMY6XUNEIZ5Y3FT42N/graph.json","events_json":"https://pith.science/api/pith-number/RYCK2LVMHMY6XUNEIZ5Y3FT42N/events.json","paper":"https://pith.science/paper/RYCK2LVM"},"agent_actions":{"view_html":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N","download_json":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N.json","view_paper":"https://pith.science/paper/RYCK2LVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10407&json=true","fetch_graph":"https://pith.science/api/pith-number/RYCK2LVMHMY6XUNEIZ5Y3FT42N/graph.json","fetch_events":"https://pith.science/api/pith-number/RYCK2LVMHMY6XUNEIZ5Y3FT42N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N/action/storage_attestation","attest_author":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N/action/author_attestation","sign_citation":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N/action/citation_signature","submit_replication":"https://pith.science/pith/RYCK2LVMHMY6XUNEIZ5Y3FT42N/action/replication_record"}},"created_at":"2026-07-05T01:35:34.018664+00:00","updated_at":"2026-07-05T01:35:34.018664+00:00"}