{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YO7F7FTZZR4J4XZDT3NFDEZ7XA","short_pith_number":"pith:YO7F7FTZ","schema_version":"1.0","canonical_sha256":"c3be5f9679cc789e5f239eda51933fb807863a0a251d594facb739dc07d67a76","source":{"kind":"arxiv","id":"2305.08067","version":1},"attestation_state":"computed","paper":{"title":"Improving End-to-End SLU performance with Prosodic Attention and Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Shangeth Rajaa","submitted_at":"2023-05-14T04:38:20Z","abstract_excerpt":"Most End-to-End SLU methods depend on the pretrained ASR or language model features for intent prediction. However, other essential information in speech, such as prosody, is often ignored. Recent research has shown improved results in classifying dialogue acts by incorporating prosodic information. The margins of improvement in these methods are minimal as the neural models ignore prosodic features. In this work, we propose prosody-attention, which uses the prosodic features differently to generate attention maps across time frames of the utterance. Then we propose prosody-distillation to exp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.08067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T04:38:20Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"ce6fb7c2433352fdf968e1558065682e079b7e87217f86a6779460ff2baf4ff8","abstract_canon_sha256":"220ecdfd1fb13d032cc3437ae89ebfe16e3737f2a8645719d5499531774356fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:57.453713Z","signature_b64":"cRTqn5MO9Z0xHHZcOk8vHvIEnUGettkVWTGvTnZyxuAJ6ZY7kDuGlD0SAyxB6H0bfG377yg5BNrWforSd5PZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3be5f9679cc789e5f239eda51933fb807863a0a251d594facb739dc07d67a76","last_reissued_at":"2026-07-05T06:09:57.453288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:57.453288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving End-to-End SLU performance with Prosodic Attention and Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Shangeth Rajaa","submitted_at":"2023-05-14T04:38:20Z","abstract_excerpt":"Most End-to-End SLU methods depend on the pretrained ASR or language model features for intent prediction. However, other essential information in speech, such as prosody, is often ignored. Recent research has shown improved results in classifying dialogue acts by incorporating prosodic information. The margins of improvement in these methods are minimal as the neural models ignore prosodic features. In this work, we propose prosody-attention, which uses the prosodic features differently to generate attention maps across time frames of the utterance. Then we propose prosody-distillation to exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08067","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/2305.08067/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.08067","created_at":"2026-07-05T06:09:57.453350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08067v1","created_at":"2026-07-05T06:09:57.453350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08067","created_at":"2026-07-05T06:09:57.453350+00:00"},{"alias_kind":"pith_short_12","alias_value":"YO7F7FTZZR4J","created_at":"2026-07-05T06:09:57.453350+00:00"},{"alias_kind":"pith_short_16","alias_value":"YO7F7FTZZR4J4XZD","created_at":"2026-07-05T06:09:57.453350+00:00"},{"alias_kind":"pith_short_8","alias_value":"YO7F7FTZ","created_at":"2026-07-05T06:09:57.453350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04814","citing_title":"Pitch Accent Detection improves Pretrained Automatic Speech Recognition","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA","json":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA.json","graph_json":"https://pith.science/api/pith-number/YO7F7FTZZR4J4XZDT3NFDEZ7XA/graph.json","events_json":"https://pith.science/api/pith-number/YO7F7FTZZR4J4XZDT3NFDEZ7XA/events.json","paper":"https://pith.science/paper/YO7F7FTZ"},"agent_actions":{"view_html":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA","download_json":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA.json","view_paper":"https://pith.science/paper/YO7F7FTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08067&json=true","fetch_graph":"https://pith.science/api/pith-number/YO7F7FTZZR4J4XZDT3NFDEZ7XA/graph.json","fetch_events":"https://pith.science/api/pith-number/YO7F7FTZZR4J4XZDT3NFDEZ7XA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA/action/storage_attestation","attest_author":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA/action/author_attestation","sign_citation":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA/action/citation_signature","submit_replication":"https://pith.science/pith/YO7F7FTZZR4J4XZDT3NFDEZ7XA/action/replication_record"}},"created_at":"2026-07-05T06:09:57.453350+00:00","updated_at":"2026-07-05T06:09:57.453350+00:00"}