{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UFP466CLGLMLOVJCFBLHBL6K47","short_pith_number":"pith:UFP466CL","canonical_record":{"source":{"id":"2211.00325","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-01T08:25:11Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b98ee99065b47b757bb020cbaecabb0057813719ce249edbd6ffa422cb8a9d11","abstract_canon_sha256":"f32035b02714925a5c89ba10301478a67f885361ab35043f602fb757eeb26afb"},"schema_version":"1.0"},"canonical_sha256":"a15fcf784b32d8b75522285670afcae7da1d8622715c42db21544629efc257e6","source":{"kind":"arxiv","id":"2211.00325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00325","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00325v1","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00325","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"UFP466CLGLML","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"UFP466CLGLMLOVJC","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"UFP466CL","created_at":"2026-07-05T05:12:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UFP466CLGLMLOVJCFBLHBL6K47","target":"record","payload":{"canonical_record":{"source":{"id":"2211.00325","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-01T08:25:11Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b98ee99065b47b757bb020cbaecabb0057813719ce249edbd6ffa422cb8a9d11","abstract_canon_sha256":"f32035b02714925a5c89ba10301478a67f885361ab35043f602fb757eeb26afb"},"schema_version":"1.0"},"canonical_sha256":"a15fcf784b32d8b75522285670afcae7da1d8622715c42db21544629efc257e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:21.258552Z","signature_b64":"0sAlJWnmzR3O8akDqYm2bzfAk5yERi4/O0vuv29siJG4d8m3QqfAheX6Zpg+d/hGqndImBdmqWFT7bm1hyYFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a15fcf784b32d8b75522285670afcae7da1d8622715c42db21544629efc257e6","last_reissued_at":"2026-07-05T05:12:21.258137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:21.258137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.00325","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6Q80lrLD9x/rfbyMFrAdP08wqcySbCshMSLmN6cBnU5WgFWh2GpYgw29IdAKQjFKQoOOrtLS+8rWaHXcoeFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:03:10.258888Z"},"content_sha256":"ef29eb4bde5d71969f8f95dd3415e7353c0e82cd0dbf319cdb45a5988cb74ced","schema_version":"1.0","event_id":"sha256:ef29eb4bde5d71969f8f95dd3415e7353c0e82cd0dbf319cdb45a5988cb74ced"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UFP466CLGLMLOVJCFBLHBL6K47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech-text based multi-modal training with bidirectional attention for improved speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Eng Siong Chng, Haihua Xu, Hao Huang, Sheng Li, Yuhang Yang","submitted_at":"2022-11-01T08:25:11Z","abstract_excerpt":"To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders. In this paper we propose to employ a novel bidirectional attention mechanism (BiAM) to jointly learn both ASR encoder (bottom layers) and text encoder with a multi-modal learning method. The BiAM is to facilitate feature sampling rate exchange, realizing the quality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00325","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/2211.00325/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wTXuwg8niLFpON35wWGQ4VVDjeXT6dTTPxJcm7KhmpOSn6lwgEHRa0pOYSgu0WBjyFOMNK6eAX42AeUb0onxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:03:10.259260Z"},"content_sha256":"38eb465864ee0984ebc6a8e078cef7a7c6feb8c8ea1b87846800d85138b0a977","schema_version":"1.0","event_id":"sha256:38eb465864ee0984ebc6a8e078cef7a7c6feb8c8ea1b87846800d85138b0a977"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFP466CLGLMLOVJCFBLHBL6K47/bundle.json","state_url":"https://pith.science/pith/UFP466CLGLMLOVJCFBLHBL6K47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFP466CLGLMLOVJCFBLHBL6K47/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T02:03:10Z","links":{"resolver":"https://pith.science/pith/UFP466CLGLMLOVJCFBLHBL6K47","bundle":"https://pith.science/pith/UFP466CLGLMLOVJCFBLHBL6K47/bundle.json","state":"https://pith.science/pith/UFP466CLGLMLOVJCFBLHBL6K47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFP466CLGLMLOVJCFBLHBL6K47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UFP466CLGLMLOVJCFBLHBL6K47","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":"f32035b02714925a5c89ba10301478a67f885361ab35043f602fb757eeb26afb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-01T08:25:11Z","title_canon_sha256":"b98ee99065b47b757bb020cbaecabb0057813719ce249edbd6ffa422cb8a9d11"},"schema_version":"1.0","source":{"id":"2211.00325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00325","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00325v1","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00325","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"UFP466CLGLML","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"UFP466CLGLMLOVJC","created_at":"2026-07-05T05:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"UFP466CL","created_at":"2026-07-05T05:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:38eb465864ee0984ebc6a8e078cef7a7c6feb8c8ea1b87846800d85138b0a977","target":"graph","created_at":"2026-07-05T05:12:21Z","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/2211.00325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and language (aka text data); 2) the homogeneity of the learned representations from two encoders. In this paper we propose to employ a novel bidirectional attention mechanism (BiAM) to jointly learn both ASR encoder (bottom layers) and text encoder with a multi-modal learning method. The BiAM is to facilitate feature sampling rate exchange, realizing the quality ","authors_text":"Eng Siong Chng, Haihua Xu, Hao Huang, Sheng Li, Yuhang Yang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-01T08:25:11Z","title":"Speech-text based multi-modal training with bidirectional attention for improved speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00325","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:ef29eb4bde5d71969f8f95dd3415e7353c0e82cd0dbf319cdb45a5988cb74ced","target":"record","created_at":"2026-07-05T05:12:21Z","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":"f32035b02714925a5c89ba10301478a67f885361ab35043f602fb757eeb26afb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-01T08:25:11Z","title_canon_sha256":"b98ee99065b47b757bb020cbaecabb0057813719ce249edbd6ffa422cb8a9d11"},"schema_version":"1.0","source":{"id":"2211.00325","kind":"arxiv","version":1}},"canonical_sha256":"a15fcf784b32d8b75522285670afcae7da1d8622715c42db21544629efc257e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a15fcf784b32d8b75522285670afcae7da1d8622715c42db21544629efc257e6","first_computed_at":"2026-07-05T05:12:21.258137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:21.258137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0sAlJWnmzR3O8akDqYm2bzfAk5yERi4/O0vuv29siJG4d8m3QqfAheX6Zpg+d/hGqndImBdmqWFT7bm1hyYFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:21.258552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.00325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef29eb4bde5d71969f8f95dd3415e7353c0e82cd0dbf319cdb45a5988cb74ced","sha256:38eb465864ee0984ebc6a8e078cef7a7c6feb8c8ea1b87846800d85138b0a977"],"state_sha256":"406cea2ab68ced9de83c6b7b7105fd429e18de6906dd4d73637b324e13fa27f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZBScYTQBu/MYQC7eFKNYtV4sliZTFXpN4hjbQBfHox9mqqt/SH0RquafNMW3w7bl3oGmkhIQuKW/Yhkcdf6pCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:03:10.261177Z","bundle_sha256":"8074f233f0b21742018c2a04eb18b9c017c917d179e0d458faaa00f0a5fb2676"}}