{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BYJOMD6E4QKAWG7W3RWDUFQM7M","short_pith_number":"pith:BYJOMD6E","canonical_record":{"source":{"id":"1811.04903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T18:42:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"192a61aa63e393c11418c9a4a389801104f9bf022ff2169ff62812ac16979fd6","abstract_canon_sha256":"93f5f2cb916bbc9a2840aa99a08928043c74245f524226c45ab2590774853f7f"},"schema_version":"1.0"},"canonical_sha256":"0e12e60fc4e4140b1bf6dc6c3a160cfb1d183fa69fe4b43955effdb0252065b0","source":{"kind":"arxiv","id":"1811.04903","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.04903","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1811.04903v2","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04903","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"BYJOMD6E4QKA","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BYJOMD6E4QKAWG7W","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BYJOMD6E","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BYJOMD6E4QKAWG7W3RWDUFQM7M","target":"record","payload":{"canonical_record":{"source":{"id":"1811.04903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T18:42:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"192a61aa63e393c11418c9a4a389801104f9bf022ff2169ff62812ac16979fd6","abstract_canon_sha256":"93f5f2cb916bbc9a2840aa99a08928043c74245f524226c45ab2590774853f7f"},"schema_version":"1.0"},"canonical_sha256":"0e12e60fc4e4140b1bf6dc6c3a160cfb1d183fa69fe4b43955effdb0252065b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:41.568093Z","signature_b64":"kWE1q3CNRg9QOnujOMHi84JcFSlOZWd9vYumsTuqTZAsbZubDsAU/HncwblKE94NxyNXWz5pm0jbODtK9nJzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e12e60fc4e4140b1bf6dc6c3a160cfb1d183fa69fe4b43955effdb0252065b0","last_reissued_at":"2026-05-17T23:53:41.567560Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:41.567560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.04903","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2HtCVirVx72abrN3QSW39m6q3iA9PHkfJDGLhzd1z6ssg08uTfvIbNV6xoeTLjTNpkyNCzPlxLJB4R04Y+KIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:11:35.144214Z"},"content_sha256":"5862c0a8a98c32efe3bc619a20d185475433040f10758fb3e85b188d44fef76d","schema_version":"1.0","event_id":"sha256:5862c0a8a98c32efe3bc619a20d185475433040f10758fb3e85b188d44fef76d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BYJOMD6E4QKAWG7W3RWDUFQM7M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stream attention-based multi-array end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hynek Hermansky, Ruizhi Li, Shinji Watanabe, Sri Harish Mallid, Takaaki Hori, Xiaofei Wang","submitted_at":"2018-11-12T18:42:33Z","abstract_excerpt":"Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array shares and contributes is crucial in this task. Motivated by the advances of joint Connectionist Temporal Classification (CTC)/attention mechanism in the End-to-End (E2E) ASR, a stream attention-based multi-array framework is proposed in this work. Microphone arrays, acting as information streams, are activated by separate encoders and decoded under the instruction of both CTC and attention networks. In terms of atte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04903","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":""},"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":"2026-05-17T23:53:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zje1jsTBrq5n7ra3t7hh3hHMjujQfgQ0djjPCIYCJk1hLLeIB8SI8hRSZHWHJrB2FVutsqf6pgrVCwhpfkfvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:11:35.144621Z"},"content_sha256":"3f3a65c42c789ae3566f02e5c91d377d54f19f7e2195cd4b6061687013412c85","schema_version":"1.0","event_id":"sha256:3f3a65c42c789ae3566f02e5c91d377d54f19f7e2195cd4b6061687013412c85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M/bundle.json","state_url":"https://pith.science/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M/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":"2026-05-29T18:11:35Z","links":{"resolver":"https://pith.science/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M","bundle":"https://pith.science/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M/bundle.json","state":"https://pith.science/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYJOMD6E4QKAWG7W3RWDUFQM7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BYJOMD6E4QKAWG7W3RWDUFQM7M","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":"93f5f2cb916bbc9a2840aa99a08928043c74245f524226c45ab2590774853f7f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T18:42:33Z","title_canon_sha256":"192a61aa63e393c11418c9a4a389801104f9bf022ff2169ff62812ac16979fd6"},"schema_version":"1.0","source":{"id":"1811.04903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.04903","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1811.04903v2","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04903","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"BYJOMD6E4QKA","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BYJOMD6E4QKAWG7W","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BYJOMD6E","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:3f3a65c42c789ae3566f02e5c91d377d54f19f7e2195cd4b6061687013412c85","target":"graph","created_at":"2026-05-17T23:53:41Z","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"},"paper":{"abstract_excerpt":"Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array shares and contributes is crucial in this task. Motivated by the advances of joint Connectionist Temporal Classification (CTC)/attention mechanism in the End-to-End (E2E) ASR, a stream attention-based multi-array framework is proposed in this work. Microphone arrays, acting as information streams, are activated by separate encoders and decoded under the instruction of both CTC and attention networks. In terms of atte","authors_text":"Hynek Hermansky, Ruizhi Li, Shinji Watanabe, Sri Harish Mallid, Takaaki Hori, Xiaofei Wang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T18:42:33Z","title":"Stream attention-based multi-array end-to-end speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04903","kind":"arxiv","version":2},"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":"sha256:5862c0a8a98c32efe3bc619a20d185475433040f10758fb3e85b188d44fef76d","target":"record","created_at":"2026-05-17T23:53:41Z","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":"93f5f2cb916bbc9a2840aa99a08928043c74245f524226c45ab2590774853f7f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T18:42:33Z","title_canon_sha256":"192a61aa63e393c11418c9a4a389801104f9bf022ff2169ff62812ac16979fd6"},"schema_version":"1.0","source":{"id":"1811.04903","kind":"arxiv","version":2}},"canonical_sha256":"0e12e60fc4e4140b1bf6dc6c3a160cfb1d183fa69fe4b43955effdb0252065b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e12e60fc4e4140b1bf6dc6c3a160cfb1d183fa69fe4b43955effdb0252065b0","first_computed_at":"2026-05-17T23:53:41.567560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:41.567560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kWE1q3CNRg9QOnujOMHi84JcFSlOZWd9vYumsTuqTZAsbZubDsAU/HncwblKE94NxyNXWz5pm0jbODtK9nJzCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:41.568093Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.04903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5862c0a8a98c32efe3bc619a20d185475433040f10758fb3e85b188d44fef76d","sha256:3f3a65c42c789ae3566f02e5c91d377d54f19f7e2195cd4b6061687013412c85"],"state_sha256":"b81389c63cdb40987ed33d31b8e93efdeb45adca616ea2aa5b106dd149a85fec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kV56BcmRSxY2fNaM0vSZ/GqHyqm+HcXS9nConvT+QWHTrY7bb3nXR63ufmog5s4c9rlpt+cJnEcVkPEI6LMeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:11:35.146625Z","bundle_sha256":"d67da3e9d7cf98c610e09786b99b422a12c99aff43024efc07657c3d85791ce0"}}