{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4F442CAZ2WALBHP5H7Q4HCEFQV","short_pith_number":"pith:4F442CAZ","schema_version":"1.0","canonical_sha256":"e179cd0819d580b09dfd3fe1c388858578b0dd95e3a4b706d7703a2e3a8da36a","source":{"kind":"arxiv","id":"1701.02477","version":1},"attestation_state":"computed","paper":{"title":"Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinav Thanda, Shankar M Venkatesan","submitted_at":"2017-01-10T08:47:56Z","abstract_excerpt":"Multi-task learning (MTL) involves the simultaneous training of two or more related tasks over shared representations. In this work, we apply MTL to audio-visual automatic speech recognition(AV-ASR). Our primary task is to learn a mapping between audio-visual fused features and frame labels obtained from acoustic GMM/HMM model. This is combined with an auxiliary task which maps visual features to frame labels obtained from a separate visual GMM/HMM model. The MTL model is tested at various levels of babble noise and the results are compared with a base-line hybrid DNN-HMM AV-ASR model. Our res"},"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":"1701.02477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-10T08:47:56Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"b93e572310c1a93f31af2a25f37dfbddfaafff56ea2a58afedae6bcfd047258d","abstract_canon_sha256":"cec9555b8903c0c04c50d076d135f415befd2e1d1988b8b5cf9d20a884f3faa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:04.173340Z","signature_b64":"KsFEZ94Uh2PoEov5c/3xpKGtJdF3xPm6Qm5FxDF+DzVTSoTYkRO9wdLLREoOd+3OVwRrV0xMsS1o2d4LSsF2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e179cd0819d580b09dfd3fe1c388858578b0dd95e3a4b706d7703a2e3a8da36a","last_reissued_at":"2026-05-18T00:53:04.172630Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:04.172630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhinav Thanda, Shankar M Venkatesan","submitted_at":"2017-01-10T08:47:56Z","abstract_excerpt":"Multi-task learning (MTL) involves the simultaneous training of two or more related tasks over shared representations. In this work, we apply MTL to audio-visual automatic speech recognition(AV-ASR). Our primary task is to learn a mapping between audio-visual fused features and frame labels obtained from acoustic GMM/HMM model. This is combined with an auxiliary task which maps visual features to frame labels obtained from a separate visual GMM/HMM model. The MTL model is tested at various levels of babble noise and the results are compared with a base-line hybrid DNN-HMM AV-ASR model. Our res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02477","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":"1701.02477","created_at":"2026-05-18T00:53:04.172728+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.02477v1","created_at":"2026-05-18T00:53:04.172728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02477","created_at":"2026-05-18T00:53:04.172728+00:00"},{"alias_kind":"pith_short_12","alias_value":"4F442CAZ2WAL","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"4F442CAZ2WALBHP5","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"4F442CAZ","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.12170","citing_title":"LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2504.13102","citing_title":"A Multi-task Learning Balanced Attention Convolutional Neural Network Model for Few-shot Underwater Acoustic Target Recognition","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV","json":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV.json","graph_json":"https://pith.science/api/pith-number/4F442CAZ2WALBHP5H7Q4HCEFQV/graph.json","events_json":"https://pith.science/api/pith-number/4F442CAZ2WALBHP5H7Q4HCEFQV/events.json","paper":"https://pith.science/paper/4F442CAZ"},"agent_actions":{"view_html":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV","download_json":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV.json","view_paper":"https://pith.science/paper/4F442CAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.02477&json=true","fetch_graph":"https://pith.science/api/pith-number/4F442CAZ2WALBHP5H7Q4HCEFQV/graph.json","fetch_events":"https://pith.science/api/pith-number/4F442CAZ2WALBHP5H7Q4HCEFQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV/action/storage_attestation","attest_author":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV/action/author_attestation","sign_citation":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV/action/citation_signature","submit_replication":"https://pith.science/pith/4F442CAZ2WALBHP5H7Q4HCEFQV/action/replication_record"}},"created_at":"2026-05-18T00:53:04.172728+00:00","updated_at":"2026-05-18T00:53:04.172728+00:00"}