{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZW7QPK3OXBRVIWCBKSHXG2VQ7B","short_pith_number":"pith:ZW7QPK3O","schema_version":"1.0","canonical_sha256":"cdbf07ab6eb863545841548f736ab0f84deb4794155ed6322676e7011a36c522","source":{"kind":"arxiv","id":"2306.05245","version":1},"attestation_state":"computed","paper":{"title":"Matching Latent Encoding for Audio-Text based Keyword Spotting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Devang Naik, Kumari Nishu, Minsik Cho","submitted_at":"2023-06-08T14:44:23Z","abstract_excerpt":"Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely unsolved. In this paper, we propose an audio-text-based end-to-end model architecture for flexible keyword spotting (KWS), which builds upon learned audio and text embeddings. Our architecture uses a novel dynamic programming-based algorithm, Dynamic Sequence Partitioning (DSP), to optimally partition the audio sequence into the same length as the word-based text"},"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":"2306.05245","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T14:44:23Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"fff650b8a8d661f722264a644f0ac6b9fd4b0e821a79eb04aa0c669ccf622751","abstract_canon_sha256":"c11dd7b89747427435fd8c772fbf0a957cbbc54e4e61844433aca41dc9bbb7d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:54.454330Z","signature_b64":"XX+7amQdl+Jv0WMRMFEv8Z+oxaF2+9Ek+xvXRb7xDuPKwYR3f0MPwW+BDTU2CS53adHodIdeNoyngtxvoX3rCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdbf07ab6eb863545841548f736ab0f84deb4794155ed6322676e7011a36c522","last_reissued_at":"2026-07-05T06:18:54.453818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:54.453818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matching Latent Encoding for Audio-Text based Keyword Spotting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Devang Naik, Kumari Nishu, Minsik Cho","submitted_at":"2023-06-08T14:44:23Z","abstract_excerpt":"Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely unsolved. In this paper, we propose an audio-text-based end-to-end model architecture for flexible keyword spotting (KWS), which builds upon learned audio and text embeddings. Our architecture uses a novel dynamic programming-based algorithm, Dynamic Sequence Partitioning (DSP), to optimally partition the audio sequence into the same length as the word-based text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05245","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/2306.05245/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":"2306.05245","created_at":"2026-07-05T06:18:54.453879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05245v1","created_at":"2026-07-05T06:18:54.453879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05245","created_at":"2026-07-05T06:18:54.453879+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZW7QPK3OXBRV","created_at":"2026-07-05T06:18:54.453879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZW7QPK3OXBRVIWCB","created_at":"2026-07-05T06:18:54.453879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZW7QPK3O","created_at":"2026-07-05T06:18:54.453879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11631","citing_title":"Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B","json":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B.json","graph_json":"https://pith.science/api/pith-number/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/graph.json","events_json":"https://pith.science/api/pith-number/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/events.json","paper":"https://pith.science/paper/ZW7QPK3O"},"agent_actions":{"view_html":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B","download_json":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B.json","view_paper":"https://pith.science/paper/ZW7QPK3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05245&json=true","fetch_graph":"https://pith.science/api/pith-number/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/action/storage_attestation","attest_author":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/action/author_attestation","sign_citation":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/action/citation_signature","submit_replication":"https://pith.science/pith/ZW7QPK3OXBRVIWCBKSHXG2VQ7B/action/replication_record"}},"created_at":"2026-07-05T06:18:54.453879+00:00","updated_at":"2026-07-05T06:18:54.453879+00:00"}