{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:43QWM66NGAPVZFRLE3S5DTFYLR","short_pith_number":"pith:43QWM66N","canonical_record":{"source":{"id":"2009.04107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-09-09T05:06:44Z","cross_cats_sorted":["cs.MM","cs.SD","eess.IV"],"title_canon_sha256":"56177efed0c9e303b31475071f1c69869a974df1df58976545baf1428d80569d","abstract_canon_sha256":"a1827e3058e66d5013522db8a4e9ef7852dd69aaa0c6a1c41d77a0f36001203d"},"schema_version":"1.0"},"canonical_sha256":"e6e1667bcd301f5c962b26e5d1ccb85c40ea0db4098b8119e62d04d1b374fff6","source":{"kind":"arxiv","id":"2009.04107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04107","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04107v1","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04107","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"43QWM66NGAPV","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"43QWM66NGAPVZFRL","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"43QWM66N","created_at":"2026-07-05T01:34:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:43QWM66NGAPVZFRLE3S5DTFYLR","target":"record","payload":{"canonical_record":{"source":{"id":"2009.04107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-09-09T05:06:44Z","cross_cats_sorted":["cs.MM","cs.SD","eess.IV"],"title_canon_sha256":"56177efed0c9e303b31475071f1c69869a974df1df58976545baf1428d80569d","abstract_canon_sha256":"a1827e3058e66d5013522db8a4e9ef7852dd69aaa0c6a1c41d77a0f36001203d"},"schema_version":"1.0"},"canonical_sha256":"e6e1667bcd301f5c962b26e5d1ccb85c40ea0db4098b8119e62d04d1b374fff6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:14.896038Z","signature_b64":"4FfFeYsyMkjpPM9RpUFqlxMc0GLNoUEMNIl2GgsJIX32GZUPO1BlF7K8HYIy9MSBho+5dtzdbiQTf8JQCNPQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e1667bcd301f5c962b26e5d1ccb85c40ea0db4098b8119e62d04d1b374fff6","last_reissued_at":"2026-07-05T01:34:14.895543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:14.895543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.04107","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":"2026-07-05T01:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MepqBJtf7MA/wsLBwx5SiwyR59nU1+tHUoKAdL/Aw7vrJIsG1eE6B8n44gcfxGJQtDoEdfFsDfmvtifg/MivBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:45:23.951983Z"},"content_sha256":"e5f6316e6e2d4c71d728fc5be15f452ae349065ea68e134a543adbc2dded9f61","schema_version":"1.0","event_id":"sha256:e5f6316e6e2d4c71d728fc5be15f452ae349065ea68e134a543adbc2dded9f61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:43QWM66NGAPVZFRLE3S5DTFYLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-modal Attention for Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Jichen Yang, Zexu Pan, Zhaojie Luo","submitted_at":"2020-09-09T05:06:44Z","abstract_excerpt":"Emotion represents an essential aspect of human speech that is manifested in speech prosody. Speech, visual, and textual cues are complementary in human communication. In this paper, we study a hybrid fusion method, referred to as multi-modal attention network (MMAN) to make use of visual and textual cues in speech emotion recognition. We propose a novel multi-modal attention mechanism, cLSTM-MMA, which facilitates the attention across three modalities and selectively fuse the information. cLSTM-MMA is fused with other uni-modal sub-networks in the late fusion. The experiments show that speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04107","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/2009.04107/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":"2026-07-05T01:34:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNwOJahTjSsJzDOCDOu1F//Gg/7sT2ehjMiRvaUzZeTo/5iivT+APcpx5EOypVRtFA8732Otw3uP5oPFZjE6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:45:23.952506Z"},"content_sha256":"74e9f47ae03836d14ce2ede943018346ab00084e31a21e8ae1fbe1c46159fd74","schema_version":"1.0","event_id":"sha256:74e9f47ae03836d14ce2ede943018346ab00084e31a21e8ae1fbe1c46159fd74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/43QWM66NGAPVZFRLE3S5DTFYLR/bundle.json","state_url":"https://pith.science/pith/43QWM66NGAPVZFRLE3S5DTFYLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/43QWM66NGAPVZFRLE3S5DTFYLR/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":"2026-08-08T15:45:23Z","links":{"resolver":"https://pith.science/pith/43QWM66NGAPVZFRLE3S5DTFYLR","bundle":"https://pith.science/pith/43QWM66NGAPVZFRLE3S5DTFYLR/bundle.json","state":"https://pith.science/pith/43QWM66NGAPVZFRLE3S5DTFYLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/43QWM66NGAPVZFRLE3S5DTFYLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:43QWM66NGAPVZFRLE3S5DTFYLR","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":"a1827e3058e66d5013522db8a4e9ef7852dd69aaa0c6a1c41d77a0f36001203d","cross_cats_sorted":["cs.MM","cs.SD","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-09-09T05:06:44Z","title_canon_sha256":"56177efed0c9e303b31475071f1c69869a974df1df58976545baf1428d80569d"},"schema_version":"1.0","source":{"id":"2009.04107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.04107","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"arxiv_version","alias_value":"2009.04107v1","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.04107","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"pith_short_12","alias_value":"43QWM66NGAPV","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"pith_short_16","alias_value":"43QWM66NGAPVZFRL","created_at":"2026-07-05T01:34:14Z"},{"alias_kind":"pith_short_8","alias_value":"43QWM66N","created_at":"2026-07-05T01:34:14Z"}],"graph_snapshots":[{"event_id":"sha256:74e9f47ae03836d14ce2ede943018346ab00084e31a21e8ae1fbe1c46159fd74","target":"graph","created_at":"2026-07-05T01:34:14Z","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/2009.04107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotion represents an essential aspect of human speech that is manifested in speech prosody. Speech, visual, and textual cues are complementary in human communication. In this paper, we study a hybrid fusion method, referred to as multi-modal attention network (MMAN) to make use of visual and textual cues in speech emotion recognition. We propose a novel multi-modal attention mechanism, cLSTM-MMA, which facilitates the attention across three modalities and selectively fuse the information. cLSTM-MMA is fused with other uni-modal sub-networks in the late fusion. The experiments show that speech","authors_text":"Haizhou Li, Jichen Yang, Zexu Pan, Zhaojie Luo","cross_cats":["cs.MM","cs.SD","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-09-09T05:06:44Z","title":"Multi-modal Attention for Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.04107","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:e5f6316e6e2d4c71d728fc5be15f452ae349065ea68e134a543adbc2dded9f61","target":"record","created_at":"2026-07-05T01:34:14Z","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":"a1827e3058e66d5013522db8a4e9ef7852dd69aaa0c6a1c41d77a0f36001203d","cross_cats_sorted":["cs.MM","cs.SD","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-09-09T05:06:44Z","title_canon_sha256":"56177efed0c9e303b31475071f1c69869a974df1df58976545baf1428d80569d"},"schema_version":"1.0","source":{"id":"2009.04107","kind":"arxiv","version":1}},"canonical_sha256":"e6e1667bcd301f5c962b26e5d1ccb85c40ea0db4098b8119e62d04d1b374fff6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6e1667bcd301f5c962b26e5d1ccb85c40ea0db4098b8119e62d04d1b374fff6","first_computed_at":"2026-07-05T01:34:14.895543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:14.895543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4FfFeYsyMkjpPM9RpUFqlxMc0GLNoUEMNIl2GgsJIX32GZUPO1BlF7K8HYIy9MSBho+5dtzdbiQTf8JQCNPQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:14.896038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.04107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5f6316e6e2d4c71d728fc5be15f452ae349065ea68e134a543adbc2dded9f61","sha256:74e9f47ae03836d14ce2ede943018346ab00084e31a21e8ae1fbe1c46159fd74"],"state_sha256":"6450982186ea9edc530dbe5493628c001913f58cba2ad8048b049894cdb3e451"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gj89V9I/6aKdlndmFm/YhqjMIW2gMNB+2ErwPZHPSZ+hDv2PMg7d9jbmipvx2pWewrtyFjBGHN42IviAi+HqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:45:23.957770Z","bundle_sha256":"af699752be211712da82738038ce1bfa2161f009623f1a7f1ea8cf81066240d6"}}