{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HVQQ2VVHVACZCMOYV6WR6ALXFJ","short_pith_number":"pith:HVQQ2VVH","schema_version":"1.0","canonical_sha256":"3d610d56a7a8059131d8afad1f01772a6cf85571afb666b3ff3dd11bddb07a99","source":{"kind":"arxiv","id":"2010.11338","version":2},"attestation_state":"computed","paper":{"title":"A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhan Wang, Dmitriy Genzel, Juan Pino, Xutai Ma, Yun Tang","submitted_at":"2020-10-21T22:40:43Z","abstract_excerpt":"Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data. This presents a challenge for speech applications where labelled speech data is very expensive to obtain, such as automatic speech recognition (ASR) and speech translation (ST). In this study, we propose a general multi-task learning framework to leverage text data for ASR and ST tasks. Two auxiliary tasks, a denoising autoencoder task and machine translati"},"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":"2010.11338","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T22:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"dda2cf28292b350947c717e027953471fc764623c8fff93e8eec062997f04eba","abstract_canon_sha256":"1a933c07bc54d86b5ac8c28f91e2d7979fe3cae78018ab1c05318e652c6a0a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:31.826626Z","signature_b64":"v/9q+xRYre+Dq5kl6TIbQRGOHH9mAsCyYyFgwUJwxRjNEFmhy46UMXPxQTI7PKd7vtffoLVlja2L5eoJ8dP4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d610d56a7a8059131d8afad1f01772a6cf85571afb666b3ff3dd11bddb07a99","last_reissued_at":"2026-07-05T02:14:31.826198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:31.826198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhan Wang, Dmitriy Genzel, Juan Pino, Xutai Ma, Yun Tang","submitted_at":"2020-10-21T22:40:43Z","abstract_excerpt":"Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data. This presents a challenge for speech applications where labelled speech data is very expensive to obtain, such as automatic speech recognition (ASR) and speech translation (ST). In this study, we propose a general multi-task learning framework to leverage text data for ASR and ST tasks. Two auxiliary tasks, a denoising autoencoder task and machine translati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11338","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/2010.11338/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":"2010.11338","created_at":"2026-07-05T02:14:31.826255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11338v2","created_at":"2026-07-05T02:14:31.826255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11338","created_at":"2026-07-05T02:14:31.826255+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVQQ2VVHVACZ","created_at":"2026-07-05T02:14:31.826255+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVQQ2VVHVACZCMOY","created_at":"2026-07-05T02:14:31.826255+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVQQ2VVH","created_at":"2026-07-05T02:14:31.826255+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/HVQQ2VVHVACZCMOYV6WR6ALXFJ","json":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ.json","graph_json":"https://pith.science/api/pith-number/HVQQ2VVHVACZCMOYV6WR6ALXFJ/graph.json","events_json":"https://pith.science/api/pith-number/HVQQ2VVHVACZCMOYV6WR6ALXFJ/events.json","paper":"https://pith.science/paper/HVQQ2VVH"},"agent_actions":{"view_html":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ","download_json":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ.json","view_paper":"https://pith.science/paper/HVQQ2VVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11338&json=true","fetch_graph":"https://pith.science/api/pith-number/HVQQ2VVHVACZCMOYV6WR6ALXFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HVQQ2VVHVACZCMOYV6WR6ALXFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ/action/storage_attestation","attest_author":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ/action/author_attestation","sign_citation":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ/action/citation_signature","submit_replication":"https://pith.science/pith/HVQQ2VVHVACZCMOYV6WR6ALXFJ/action/replication_record"}},"created_at":"2026-07-05T02:14:31.826255+00:00","updated_at":"2026-07-05T02:14:31.826255+00:00"}