{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NHCPMRU5ZW74FH4I2XG6H6KWCC","short_pith_number":"pith:NHCPMRU5","schema_version":"1.0","canonical_sha256":"69c4f6469dcdbfc29f88d5cde3f95610b487ea8315a4a67000a9fcf31ab23c55","source":{"kind":"arxiv","id":"1904.07704","version":2},"attestation_state":"computed","paper":{"title":"SpeechYOLO: Detection and Localization of Speech Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Joseph Keshet, Tzeviya Sylvia Fuchs, Yael Segal","submitted_at":"2019-04-14T15:47:14Z","abstract_excerpt":"In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm for object detection in images. The goal of SpeechYOLO is to localize boundaries of utterances within the input signal, and to correctly classify them. Our system is composed of a convolutional neural network, with a simple least-mean-squares loss function. We evaluated the system on several keyword spotting tasks, that include corpora of read speech and spon"},"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":"1904.07704","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-04-14T15:47:14Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"ba9551837a00ac6238ca5a040e99fce90ff71c7bbfe0ac0c5072649bead6abbc","abstract_canon_sha256":"930fe93774773be97cca5d2e3bd81d4693a3f795caf10b122f1f64202958c946"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:07.027090Z","signature_b64":"8x6vJyrWBfDbYLTJkOKxf0JN+l5VT2MJOoUJiZgFCJs38ENOxHBu9SuiHuZhLGT8m+0AqQrJXiq6Ah7JLTD3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c4f6469dcdbfc29f88d5cde3f95610b487ea8315a4a67000a9fcf31ab23c55","last_reissued_at":"2026-07-05T00:07:07.026652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:07.026652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechYOLO: Detection and Localization of Speech Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Joseph Keshet, Tzeviya Sylvia Fuchs, Yael Segal","submitted_at":"2019-04-14T15:47:14Z","abstract_excerpt":"In this paper, we propose to apply object detection methods from the vision domain on the speech recognition domain, by treating audio fragments as objects. More specifically, we present SpeechYOLO, which is inspired by the YOLO algorithm for object detection in images. The goal of SpeechYOLO is to localize boundaries of utterances within the input signal, and to correctly classify them. Our system is composed of a convolutional neural network, with a simple least-mean-squares loss function. We evaluated the system on several keyword spotting tasks, that include corpora of read speech and spon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07704","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/1904.07704/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":"1904.07704","created_at":"2026-07-05T00:07:07.026708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07704v2","created_at":"2026-07-05T00:07:07.026708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07704","created_at":"2026-07-05T00:07:07.026708+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHCPMRU5ZW74","created_at":"2026-07-05T00:07:07.026708+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHCPMRU5ZW74FH4I","created_at":"2026-07-05T00:07:07.026708+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHCPMRU5","created_at":"2026-07-05T00:07:07.026708+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/NHCPMRU5ZW74FH4I2XG6H6KWCC","json":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC.json","graph_json":"https://pith.science/api/pith-number/NHCPMRU5ZW74FH4I2XG6H6KWCC/graph.json","events_json":"https://pith.science/api/pith-number/NHCPMRU5ZW74FH4I2XG6H6KWCC/events.json","paper":"https://pith.science/paper/NHCPMRU5"},"agent_actions":{"view_html":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC","download_json":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC.json","view_paper":"https://pith.science/paper/NHCPMRU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/NHCPMRU5ZW74FH4I2XG6H6KWCC/graph.json","fetch_events":"https://pith.science/api/pith-number/NHCPMRU5ZW74FH4I2XG6H6KWCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC/action/storage_attestation","attest_author":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC/action/author_attestation","sign_citation":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC/action/citation_signature","submit_replication":"https://pith.science/pith/NHCPMRU5ZW74FH4I2XG6H6KWCC/action/replication_record"}},"created_at":"2026-07-05T00:07:07.026708+00:00","updated_at":"2026-07-05T00:07:07.026708+00:00"}