{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RWBYATP44PBRJ5U4B7SI5A5FZR","short_pith_number":"pith:RWBYATP4","schema_version":"1.0","canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","source":{"kind":"arxiv","id":"2011.09044","version":2},"attestation_state":"computed","paper":{"title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Athanasios Mouchtaris, Bhuvan Agrawal, Markus M\\\"uller, Martin Radfar, Samridhi Choudhary, Siegfried Kunzmann","submitted_at":"2020-11-18T02:32:42Z","abstract_excerpt":"End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings. We propose using different multi-modal losses to explicitly guide the acoustic embeddings t"},"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":"2011.09044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-18T02:32:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"a09d282ed38b434cec362946c4334775d1b2f63bca1aadab329f90f459b4d9f6","abstract_canon_sha256":"426381b2d43475e7b77b79619ed103fcafac313e0be131a042351c4120ab5019"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:25.774657Z","signature_b64":"7XADXNVO6bhkx1t2jxfPuHjEy9BgjBN4aGaUcY2DPiq/td+uBSYshNvH7B/5R4j+wAWT1qJMuWWg78Ov2eTvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d83804dfce3c314f69c0fe48e83a5cc76863405f7d2bf472738c169454ccd78","last_reissued_at":"2026-07-05T02:32:25.774170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:25.774170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Athanasios Mouchtaris, Bhuvan Agrawal, Markus M\\\"uller, Martin Radfar, Samridhi Choudhary, Siegfried Kunzmann","submitted_at":"2020-11-18T02:32:42Z","abstract_excerpt":"End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings. We propose using different multi-modal losses to explicitly guide the acoustic embeddings t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09044","kind":"arxiv","version":2},"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/2011.09044/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":"2011.09044","created_at":"2026-07-05T02:32:25.774238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.09044v2","created_at":"2026-07-05T02:32:25.774238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09044","created_at":"2026-07-05T02:32:25.774238+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWBYATP44PBR","created_at":"2026-07-05T02:32:25.774238+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWBYATP44PBRJ5U4","created_at":"2026-07-05T02:32:25.774238+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWBYATP4","created_at":"2026-07-05T02:32:25.774238+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/RWBYATP44PBRJ5U4B7SI5A5FZR","json":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR.json","graph_json":"https://pith.science/api/pith-number/RWBYATP44PBRJ5U4B7SI5A5FZR/graph.json","events_json":"https://pith.science/api/pith-number/RWBYATP44PBRJ5U4B7SI5A5FZR/events.json","paper":"https://pith.science/paper/RWBYATP4"},"agent_actions":{"view_html":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR","download_json":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR.json","view_paper":"https://pith.science/paper/RWBYATP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.09044&json=true","fetch_graph":"https://pith.science/api/pith-number/RWBYATP44PBRJ5U4B7SI5A5FZR/graph.json","fetch_events":"https://pith.science/api/pith-number/RWBYATP44PBRJ5U4B7SI5A5FZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/action/storage_attestation","attest_author":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/action/author_attestation","sign_citation":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/action/citation_signature","submit_replication":"https://pith.science/pith/RWBYATP44PBRJ5U4B7SI5A5FZR/action/replication_record"}},"created_at":"2026-07-05T02:32:25.774238+00:00","updated_at":"2026-07-05T02:32:25.774238+00:00"}