{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WONLWLZDOHE2Q4FA5DEIYDJIAV","short_pith_number":"pith:WONLWLZD","canonical_record":{"source":{"id":"2406.08353","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T15:59:25Z","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"c1401f25e4319e75b92950a0aea112d8abf50fe88c5e76704f9c689897442722","abstract_canon_sha256":"766a262047aa790980c84db35df0ca1101adc3943675fd2873accfd9f4747cb3"},"schema_version":"1.0"},"canonical_sha256":"b39abb2f2371c9a870a0e8c88c0d28057240c4d68f1ee6a4c84faa3c2af26658","source":{"kind":"arxiv","id":"2406.08353","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08353","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08353v3","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08353","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_12","alias_value":"WONLWLZDOHE2","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_16","alias_value":"WONLWLZDOHE2Q4FA","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_8","alias_value":"WONLWLZD","created_at":"2026-07-05T10:37:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WONLWLZDOHE2Q4FA5DEIYDJIAV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08353","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T15:59:25Z","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"c1401f25e4319e75b92950a0aea112d8abf50fe88c5e76704f9c689897442722","abstract_canon_sha256":"766a262047aa790980c84db35df0ca1101adc3943675fd2873accfd9f4747cb3"},"schema_version":"1.0"},"canonical_sha256":"b39abb2f2371c9a870a0e8c88c0d28057240c4d68f1ee6a4c84faa3c2af26658","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:27.198978Z","signature_b64":"afKoFRPEtXigX5/tmLq9UaR5Ev1cY32BnbPUtOIR3WT+W6pNY67iIBK8G+BeOfyT7tEubFUHXQYhrUAkCyhaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b39abb2f2371c9a870a0e8c88c0d28057240c4d68f1ee6a4c84faa3c2af26658","last_reissued_at":"2026-07-05T10:37:27.198048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:27.198048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08353","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yGG+c51JPeh+uMRCkV0dVJXEdpRtQrfuz5RbIcN8cRkhpPIGuYG2V+NWgQJTMdxc/qPPreShvSSQn7a15tlwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:56:54.963696Z"},"content_sha256":"48c987d39668e82e91004b932c7e09271bc1eddba3681b28b64c25333ef40d05","schema_version":"1.0","event_id":"sha256:48c987d39668e82e91004b932c7e09271bc1eddba3681b28b64c25333ef40d05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WONLWLZDOHE2Q4FA5DEIYDJIAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Catherine Lai, Peter Bell, Yuanchao Li","submitted_at":"2024-06-12T15:59:25Z","abstract_excerpt":"Text data is commonly utilized as a primary input to enhance Speech Emotion Recognition (SER) performance and reliability. However, the reliance on human-transcribed text in most studies impedes the development of practical SER systems, creating a gap between in-lab research and real-world scenarios where Automatic Speech Recognition (ASR) serves as the text source. Hence, this study benchmarks SER performance using ASR transcripts with varying Word Error Rates (WERs) from eleven models on three well-known corpora: IEMOCAP, CMU-MOSI, and MSP-Podcast. Our evaluation includes both text-only and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08353","kind":"arxiv","version":3},"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/2406.08353/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":"2026-07-05T10:37:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0XI0ENS+eTmy6zNPn7lmR3ujaJo58vbE/+aNh7787407uPdN0WRSWH2Z6rHDjVBGwFhM2GUxOnM4j6TpSn/PCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:56:54.964554Z"},"content_sha256":"f23cf815a4cfe8ee6f5f2778eb18ec3f68dde061c352e17b2820850227cab633","schema_version":"1.0","event_id":"sha256:f23cf815a4cfe8ee6f5f2778eb18ec3f68dde061c352e17b2820850227cab633"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV/bundle.json","state_url":"https://pith.science/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV/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":"2026-08-22T00:56:54Z","links":{"resolver":"https://pith.science/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV","bundle":"https://pith.science/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV/bundle.json","state":"https://pith.science/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WONLWLZDOHE2Q4FA5DEIYDJIAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WONLWLZDOHE2Q4FA5DEIYDJIAV","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":"766a262047aa790980c84db35df0ca1101adc3943675fd2873accfd9f4747cb3","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T15:59:25Z","title_canon_sha256":"c1401f25e4319e75b92950a0aea112d8abf50fe88c5e76704f9c689897442722"},"schema_version":"1.0","source":{"id":"2406.08353","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08353","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08353v3","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08353","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_12","alias_value":"WONLWLZDOHE2","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_16","alias_value":"WONLWLZDOHE2Q4FA","created_at":"2026-07-05T10:37:27Z"},{"alias_kind":"pith_short_8","alias_value":"WONLWLZD","created_at":"2026-07-05T10:37:27Z"}],"graph_snapshots":[{"event_id":"sha256:f23cf815a4cfe8ee6f5f2778eb18ec3f68dde061c352e17b2820850227cab633","target":"graph","created_at":"2026-07-05T10:37:27Z","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/2406.08353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text data is commonly utilized as a primary input to enhance Speech Emotion Recognition (SER) performance and reliability. However, the reliance on human-transcribed text in most studies impedes the development of practical SER systems, creating a gap between in-lab research and real-world scenarios where Automatic Speech Recognition (ASR) serves as the text source. Hence, this study benchmarks SER performance using ASR transcripts with varying Word Error Rates (WERs) from eleven models on three well-known corpora: IEMOCAP, CMU-MOSI, and MSP-Podcast. Our evaluation includes both text-only and ","authors_text":"Catherine Lai, Peter Bell, Yuanchao Li","cross_cats":["cs.CL","cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T15:59:25Z","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08353","kind":"arxiv","version":3},"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":"sha256:48c987d39668e82e91004b932c7e09271bc1eddba3681b28b64c25333ef40d05","target":"record","created_at":"2026-07-05T10:37:27Z","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":"766a262047aa790980c84db35df0ca1101adc3943675fd2873accfd9f4747cb3","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T15:59:25Z","title_canon_sha256":"c1401f25e4319e75b92950a0aea112d8abf50fe88c5e76704f9c689897442722"},"schema_version":"1.0","source":{"id":"2406.08353","kind":"arxiv","version":3}},"canonical_sha256":"b39abb2f2371c9a870a0e8c88c0d28057240c4d68f1ee6a4c84faa3c2af26658","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b39abb2f2371c9a870a0e8c88c0d28057240c4d68f1ee6a4c84faa3c2af26658","first_computed_at":"2026-07-05T10:37:27.198048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:27.198048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"afKoFRPEtXigX5/tmLq9UaR5Ev1cY32BnbPUtOIR3WT+W6pNY67iIBK8G+BeOfyT7tEubFUHXQYhrUAkCyhaAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:27.198978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08353","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48c987d39668e82e91004b932c7e09271bc1eddba3681b28b64c25333ef40d05","sha256:f23cf815a4cfe8ee6f5f2778eb18ec3f68dde061c352e17b2820850227cab633"],"state_sha256":"4794a1dc28ec94937dfda260a0761ebbfcf34cef4e8c0c4328d352031d210682"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fd3kzKbqwKZZaQ46q/mt+peuNAPlN0rnCU+FN8PfgMVnVGz53n27ZulXIMc2xDEuBx2A2kCTjKqnkOECVJ8jAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:56:54.971295Z","bundle_sha256":"5b5c3c459591304c4c44e26187c4285009ad853191eed7d0a359a1d0d9d5d807"}}