{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZYF5ZVPI2RMAC5QX64CWPSEM3M","short_pith_number":"pith:ZYF5ZVPI","schema_version":"1.0","canonical_sha256":"ce0bdcd5e8d458017617f70567c88cdb39a25e4f90f4855b139e78bdda6e4b07","source":{"kind":"arxiv","id":"1907.01367","version":1},"attestation_state":"computed","paper":{"title":"Lipper: Synthesizing Thy Speech using Multi-View Lipreading","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Khwaja Mohd. Salik, Rajiv Ratn Shah, Roger Zimmermann, Rohit Jain, Yaman Kumar, Yifang Yin","submitted_at":"2019-06-28T10:26:23Z","abstract_excerpt":"Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes representing text phrases. However, there are multiple problems associated with making lipreading a text-based classification task like its dependence on a particular language and vocabulary mapping. Thus, in this paper we propose a multi-view lipreading to audio system, namely Lipper, which models it as a regression task. The model takes silent videos as input and pr"},"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":"1907.01367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2019-06-28T10:26:23Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"88fef4bf13139a435227a453668d793ab5bacdced086205f90aa80510f3c32de","abstract_canon_sha256":"31ba71d9668fdd7a214619a247826a7d79ffc9b4133e1f80e54c3c1c0ff91f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:40.589145Z","signature_b64":"Obtc4+H9cL6oEzbToOksoJntoB8myYMX2RugA6u/uN5GTqoU5hYxkad9w65zXaxVVK6k6sdESTqMObgGbZGeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce0bdcd5e8d458017617f70567c88cdb39a25e4f90f4855b139e78bdda6e4b07","last_reissued_at":"2026-05-17T23:41:40.588669Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:40.588669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lipper: Synthesizing Thy Speech using Multi-View Lipreading","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Khwaja Mohd. Salik, Rajiv Ratn Shah, Roger Zimmermann, Rohit Jain, Yaman Kumar, Yifang Yin","submitted_at":"2019-06-28T10:26:23Z","abstract_excerpt":"Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes representing text phrases. However, there are multiple problems associated with making lipreading a text-based classification task like its dependence on a particular language and vocabulary mapping. Thus, in this paper we propose a multi-view lipreading to audio system, namely Lipper, which models it as a regression task. The model takes silent videos as input and pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01367","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":"1907.01367","created_at":"2026-05-17T23:41:40.588731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01367v1","created_at":"2026-05-17T23:41:40.588731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01367","created_at":"2026-05-17T23:41:40.588731+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYF5ZVPI2RMA","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYF5ZVPI2RMAC5QX","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYF5ZVPI","created_at":"2026-05-18T12:33:33.725879+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/ZYF5ZVPI2RMAC5QX64CWPSEM3M","json":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M.json","graph_json":"https://pith.science/api/pith-number/ZYF5ZVPI2RMAC5QX64CWPSEM3M/graph.json","events_json":"https://pith.science/api/pith-number/ZYF5ZVPI2RMAC5QX64CWPSEM3M/events.json","paper":"https://pith.science/paper/ZYF5ZVPI"},"agent_actions":{"view_html":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M","download_json":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M.json","view_paper":"https://pith.science/paper/ZYF5ZVPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01367&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYF5ZVPI2RMAC5QX64CWPSEM3M/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYF5ZVPI2RMAC5QX64CWPSEM3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M/action/storage_attestation","attest_author":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M/action/author_attestation","sign_citation":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M/action/citation_signature","submit_replication":"https://pith.science/pith/ZYF5ZVPI2RMAC5QX64CWPSEM3M/action/replication_record"}},"created_at":"2026-05-17T23:41:40.588731+00:00","updated_at":"2026-05-17T23:41:40.588731+00:00"}