{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SPTTH74LLY7TCHJPJ2VO7O6WBE","short_pith_number":"pith:SPTTH74L","schema_version":"1.0","canonical_sha256":"93e733ff8b5e3f311d2f4eaaefbbd60923ae3b5e83c0798d61e525dd3c15b3ec","source":{"kind":"arxiv","id":"1902.07817","version":1},"attestation_state":"computed","paper":{"title":"Audio-Linguistic Embeddings for Spoken Sentences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Albert Haque, Li Fei-Fei, Michelle Guo, Prateek Verma","submitted_at":"2019-02-20T23:58:29Z","abstract_excerpt":"We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence level. Formulated as an audio-linguistic multitask learning problem, our encoder-decoder model simultaneously reconstructs acoustic and natural language features from audio. Our results show that spoken sentence embeddings outperform phoneme and word-level baselines on speech recognition and emotion recognition tasks. Ablation studies show that our embeddings c"},"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":"1902.07817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-02-20T23:58:29Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"053b96a92d44df68418b3c7861ddea3bcddb24261c331b94d88226a46c740626","abstract_canon_sha256":"338dc7782d4782f25357ace1ce7ec6007e1d9d197e55b664ed963aa6cfcb4000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:03.815261Z","signature_b64":"HGbXZRJ/qIhxnLXfiRdcDUyVF/+7RVRxhhSjit9na1c0/+2oY+NntFUtuNtD3MQ3Q6yiibsDqs3A4+7guISvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93e733ff8b5e3f311d2f4eaaefbbd60923ae3b5e83c0798d61e525dd3c15b3ec","last_reissued_at":"2026-05-17T23:53:03.814685Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:03.814685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Linguistic Embeddings for Spoken Sentences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Albert Haque, Li Fei-Fei, Michelle Guo, Prateek Verma","submitted_at":"2019-02-20T23:58:29Z","abstract_excerpt":"We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence level. Formulated as an audio-linguistic multitask learning problem, our encoder-decoder model simultaneously reconstructs acoustic and natural language features from audio. Our results show that spoken sentence embeddings outperform phoneme and word-level baselines on speech recognition and emotion recognition tasks. Ablation studies show that our embeddings c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07817","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":""},"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":"1902.07817","created_at":"2026-05-17T23:53:03.814766+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.07817v1","created_at":"2026-05-17T23:53:03.814766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07817","created_at":"2026-05-17T23:53:03.814766+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPTTH74LLY7T","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPTTH74LLY7TCHJP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPTTH74L","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE","json":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE.json","graph_json":"https://pith.science/api/pith-number/SPTTH74LLY7TCHJPJ2VO7O6WBE/graph.json","events_json":"https://pith.science/api/pith-number/SPTTH74LLY7TCHJPJ2VO7O6WBE/events.json","paper":"https://pith.science/paper/SPTTH74L"},"agent_actions":{"view_html":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE","download_json":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE.json","view_paper":"https://pith.science/paper/SPTTH74L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.07817&json=true","fetch_graph":"https://pith.science/api/pith-number/SPTTH74LLY7TCHJPJ2VO7O6WBE/graph.json","fetch_events":"https://pith.science/api/pith-number/SPTTH74LLY7TCHJPJ2VO7O6WBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE/action/storage_attestation","attest_author":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE/action/author_attestation","sign_citation":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE/action/citation_signature","submit_replication":"https://pith.science/pith/SPTTH74LLY7TCHJPJ2VO7O6WBE/action/replication_record"}},"created_at":"2026-05-17T23:53:03.814766+00:00","updated_at":"2026-05-17T23:53:03.814766+00:00"}