{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TSB5CX3PHBPA5IQBG5CZWD7W6L","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":"de31170a8b61e5e51d556ae169f949425d157dc9eabf9460cd4241ff78899861","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-09T01:05:59Z","title_canon_sha256":"88d2bacd5fef890c819bc5d4376dc0ac4f58799e3f1d16712079303395c51a09"},"schema_version":"1.0","source":{"id":"2309.04654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04654","created_at":"2026-07-05T06:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04654v1","created_at":"2026-07-05T06:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04654","created_at":"2026-07-05T06:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"TSB5CX3PHBPA","created_at":"2026-07-05T06:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"TSB5CX3PHBPA5IQB","created_at":"2026-07-05T06:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"TSB5CX3P","created_at":"2026-07-05T06:49:06Z"}],"graph_snapshots":[{"event_id":"sha256:975d9e879c24b7e1412c8d4a0442bafe5cc1aeaeced6e4e0a7ac6ee17e09ce6d","target":"graph","created_at":"2026-07-05T06:49:06Z","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/2309.04654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving high accuracy with low latency has always been a challenge in streaming end-to-end automatic speech recognition (ASR) systems. By attending to more future contexts, a streaming ASR model achieves higher accuracy but results in larger latency, which hurts the streaming performance. In the Mask-CTC framework, an encoder network is trained to learn the feature representation that anticipates long-term contexts, which is desirable for streaming ASR. Mask-CTC-based encoder pre-training has been shown beneficial in achieving low latency and high accuracy for triggered attention-based ASR. ","authors_text":"Huaibo Zhao, Tetsuji Ogawa, Tetsunori Kobayashi, Yosuke Higuchi, Yusuke Kida","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-09T01:05:59Z","title":"Mask-CTC-based Encoder Pre-training for Streaming End-to-End Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04654","kind":"arxiv","version":1},"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":"sha256:543f344bbe7836187fc6d6c3246a4b3de00c175e3b497a131c3af7c179036afe","target":"record","created_at":"2026-07-05T06:49:06Z","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":"de31170a8b61e5e51d556ae169f949425d157dc9eabf9460cd4241ff78899861","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-09T01:05:59Z","title_canon_sha256":"88d2bacd5fef890c819bc5d4376dc0ac4f58799e3f1d16712079303395c51a09"},"schema_version":"1.0","source":{"id":"2309.04654","kind":"arxiv","version":1}},"canonical_sha256":"9c83d15f6f385e0ea20137459b0ff6f2fd99fc54f9fdab1293099887401f06f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c83d15f6f385e0ea20137459b0ff6f2fd99fc54f9fdab1293099887401f06f7","first_computed_at":"2026-07-05T06:49:06.926332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:06.926332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7hCRAiwcdZnnPxzhAHFWvRp8vqnhrIj83n1S2fKUhzoUwdkJzSsLrjV1IXa1rwTfSuWRh7QKfT7CNke2f+2fAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:06.926774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543f344bbe7836187fc6d6c3246a4b3de00c175e3b497a131c3af7c179036afe","sha256:975d9e879c24b7e1412c8d4a0442bafe5cc1aeaeced6e4e0a7ac6ee17e09ce6d"],"state_sha256":"850912fbb45faae051c4948bd8cd89cc8580f3165289dcc38b79f6c50f5a4b07"}