{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TWZ726YG7KGLF7OLBDXFG3HUZB","short_pith_number":"pith:TWZ726YG","schema_version":"1.0","canonical_sha256":"9db3fd7b06fa8cb2fdcb08ee536cf4c878e5ecd0302e5498c0b4c590f719e81a","source":{"kind":"arxiv","id":"2210.02904","version":1},"attestation_state":"computed","paper":{"title":"WakeUpNet: A Mobile-Transformer based Framework for End-to-End Streaming Voice Trigger","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Salah Karout, Senling Lin, Thorin Farnsworth, Zixing Zhang","submitted_at":"2022-10-06T13:18:48Z","abstract_excerpt":"End-to-end models have gradually become the main technical stream for voice trigger, aiming to achieve an utmost prediction accuracy but with a small footprint. In present paper, we propose an end-to-end voice trigger framework, namely WakeupNet, which is basically structured on a Transformer encoder. The purpose of this framework is to explore the context-capturing capability of Transformer, as sequential information is vital for wakeup-word detection. However, the conventional Transformer encoder is too large to fit our task. To address this issue, we introduce different model compression ap"},"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":"2210.02904","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-06T13:18:48Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d05f1d944b3e74d8a88b9fc7f37754fe114980129f0fd2c9a0c73bbcd73418ad","abstract_canon_sha256":"cd607260ed921ee1de560583e118029fbd5248c8991aff33e6b7e0422bc25e53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:05.198858Z","signature_b64":"Dj2UvnzjIYz4NWRBq87bfkb/i2UzFOt1aO7lSMVIK0rfh7kpuPP32DxTD9Fb7m/1xZ1CuiuK4+7+kgN1o48lAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9db3fd7b06fa8cb2fdcb08ee536cf4c878e5ecd0302e5498c0b4c590f719e81a","last_reissued_at":"2026-07-05T05:04:05.198467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:05.198467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WakeUpNet: A Mobile-Transformer based Framework for End-to-End Streaming Voice Trigger","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Salah Karout, Senling Lin, Thorin Farnsworth, Zixing Zhang","submitted_at":"2022-10-06T13:18:48Z","abstract_excerpt":"End-to-end models have gradually become the main technical stream for voice trigger, aiming to achieve an utmost prediction accuracy but with a small footprint. In present paper, we propose an end-to-end voice trigger framework, namely WakeupNet, which is basically structured on a Transformer encoder. The purpose of this framework is to explore the context-capturing capability of Transformer, as sequential information is vital for wakeup-word detection. However, the conventional Transformer encoder is too large to fit our task. To address this issue, we introduce different model compression ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02904","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/2210.02904/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":"2210.02904","created_at":"2026-07-05T05:04:05.198523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02904v1","created_at":"2026-07-05T05:04:05.198523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02904","created_at":"2026-07-05T05:04:05.198523+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWZ726YG7KGL","created_at":"2026-07-05T05:04:05.198523+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWZ726YG7KGLF7OL","created_at":"2026-07-05T05:04:05.198523+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWZ726YG","created_at":"2026-07-05T05:04:05.198523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09339","citing_title":"Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB","json":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB.json","graph_json":"https://pith.science/api/pith-number/TWZ726YG7KGLF7OLBDXFG3HUZB/graph.json","events_json":"https://pith.science/api/pith-number/TWZ726YG7KGLF7OLBDXFG3HUZB/events.json","paper":"https://pith.science/paper/TWZ726YG"},"agent_actions":{"view_html":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB","download_json":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB.json","view_paper":"https://pith.science/paper/TWZ726YG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02904&json=true","fetch_graph":"https://pith.science/api/pith-number/TWZ726YG7KGLF7OLBDXFG3HUZB/graph.json","fetch_events":"https://pith.science/api/pith-number/TWZ726YG7KGLF7OLBDXFG3HUZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB/action/storage_attestation","attest_author":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB/action/author_attestation","sign_citation":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB/action/citation_signature","submit_replication":"https://pith.science/pith/TWZ726YG7KGLF7OLBDXFG3HUZB/action/replication_record"}},"created_at":"2026-07-05T05:04:05.198523+00:00","updated_at":"2026-07-05T05:04:05.198523+00:00"}