{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RIWZEEGU5PBYEWLSYLILK5THHC","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":"08bcdf524ad99b6da1814ecc93ebed867649749880a370122f3945ef99779a7e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-28T08:38:43Z","title_canon_sha256":"ef50fe88367b100d3e3ded4de42589e9f618e9ea339a410273b74f6787141169"},"schema_version":"1.0","source":{"id":"2403.19224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19224","created_at":"2026-07-05T08:01:46Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19224v1","created_at":"2026-07-05T08:01:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19224","created_at":"2026-07-05T08:01:46Z"},{"alias_kind":"pith_short_12","alias_value":"RIWZEEGU5PBY","created_at":"2026-07-05T08:01:46Z"},{"alias_kind":"pith_short_16","alias_value":"RIWZEEGU5PBYEWLS","created_at":"2026-07-05T08:01:46Z"},{"alias_kind":"pith_short_8","alias_value":"RIWZEEGU","created_at":"2026-07-05T08:01:46Z"}],"graph_snapshots":[{"event_id":"sha256:2170099b7cbfe1e3d22d682253d925a54b7f4ddd196895dc90b9f08cde15c5e5","target":"graph","created_at":"2026-07-05T08:01:46Z","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/2403.19224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The mainstream paradigm of speech emotion recognition (SER) is identifying the single emotion label of the entire utterance. This line of works neglect the emotion dynamics at fine temporal granularity and mostly fail to leverage linguistic information of speech signal explicitly. In this paper, we propose Emotion Neural Transducer for fine-grained speech emotion recognition with automatic speech recognition (ASR) joint training. We first extend typical neural transducer with emotion joint network to construct emotion lattice for fine-grained SER. Then we propose lattice max pooling on the ali","authors_text":"Aimin Zhou, Feng Liu, Hanyang Wang, Siyuan Shen, Yu Gao","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-28T08:38:43Z","title":"Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19224","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:d465094826e67ca4a494d5566f3ebb26e002a265f28bd6482696aa77ad93c5da","target":"record","created_at":"2026-07-05T08:01:46Z","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":"08bcdf524ad99b6da1814ecc93ebed867649749880a370122f3945ef99779a7e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-28T08:38:43Z","title_canon_sha256":"ef50fe88367b100d3e3ded4de42589e9f618e9ea339a410273b74f6787141169"},"schema_version":"1.0","source":{"id":"2403.19224","kind":"arxiv","version":1}},"canonical_sha256":"8a2d9210d4ebc3825972c2d0b57667388ce64422bd8bb43659fd3e1494360654","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a2d9210d4ebc3825972c2d0b57667388ce64422bd8bb43659fd3e1494360654","first_computed_at":"2026-07-05T08:01:46.521511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:46.521511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jBVgpawPphD/XUTkAcW53QLiikUUo1DF7mgtclmAD00arugMfkFjrSPy4lV2zKJ/hG3WtsoEmhytZap0NimABA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:46.521951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d465094826e67ca4a494d5566f3ebb26e002a265f28bd6482696aa77ad93c5da","sha256:2170099b7cbfe1e3d22d682253d925a54b7f4ddd196895dc90b9f08cde15c5e5"],"state_sha256":"a9383e972240110db52101a3f1c6765da7705f2f38685cc5f03070b18e6eace1"}