{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4JVJJNTNCPX5NDNF43EVQW7C76","short_pith_number":"pith:4JVJJNTN","schema_version":"1.0","canonical_sha256":"e26a94b66d13efd68da5e6c9585be2ffb7903b1a5e204a7250abcfd52bb3c582","source":{"kind":"arxiv","id":"1702.01714","version":1},"attestation_state":"computed","paper":{"title":"DNN adaptation by automatic quality estimation of ASR hypotheses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniele Falavigna, Marco Matassoni, Marco Turchi, Matteo Negri, Shahab Jalalvand","submitted_at":"2017-02-06T17:21:39Z","abstract_excerpt":"In this paper we propose to exploit the automatic Quality Estimation (QE) of ASR hypotheses to perform the unsupervised adaptation of a deep neural network modeling acoustic probabilities. Our hypothesis is that significant improvements can be achieved by: i)automatically transcribing the evaluation data we are currently trying to recognise, and ii) selecting from it a subset of \"good quality\" instances based on the word error rate (WER) scores predicted by a QE component. To validate this hypothesis, we run several experiments on the evaluation data sets released for the CHiME-3 challenge. Fi"},"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":"1702.01714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-06T17:21:39Z","cross_cats_sorted":[],"title_canon_sha256":"e7fee31e06d91d0312b7e2c24277523c7d06e702e4fb6be2ab79ac5f1ba54abf","abstract_canon_sha256":"7af4897df8e78beb75a285821695d17e7ee5bcd796ba67dd518b1c24dab190f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:19.791124Z","signature_b64":"5fKrBa3kQGHfPMTmh0nGqHG2tToO8p0gN+luwhdz1+nhF1KbQR32qzyahHIaRBldXnwRsaHNCoTVnnRABUw3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e26a94b66d13efd68da5e6c9585be2ffb7903b1a5e204a7250abcfd52bb3c582","last_reissued_at":"2026-05-18T00:51:19.790598Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:19.790598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNN adaptation by automatic quality estimation of ASR hypotheses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniele Falavigna, Marco Matassoni, Marco Turchi, Matteo Negri, Shahab Jalalvand","submitted_at":"2017-02-06T17:21:39Z","abstract_excerpt":"In this paper we propose to exploit the automatic Quality Estimation (QE) of ASR hypotheses to perform the unsupervised adaptation of a deep neural network modeling acoustic probabilities. Our hypothesis is that significant improvements can be achieved by: i)automatically transcribing the evaluation data we are currently trying to recognise, and ii) selecting from it a subset of \"good quality\" instances based on the word error rate (WER) scores predicted by a QE component. To validate this hypothesis, we run several experiments on the evaluation data sets released for the CHiME-3 challenge. Fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01714","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":"1702.01714","created_at":"2026-05-18T00:51:19.790670+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.01714v1","created_at":"2026-05-18T00:51:19.790670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01714","created_at":"2026-05-18T00:51:19.790670+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JVJJNTNCPX5","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JVJJNTNCPX5NDNF","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JVJJNTN","created_at":"2026-05-18T12:31:00.734936+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/4JVJJNTNCPX5NDNF43EVQW7C76","json":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76.json","graph_json":"https://pith.science/api/pith-number/4JVJJNTNCPX5NDNF43EVQW7C76/graph.json","events_json":"https://pith.science/api/pith-number/4JVJJNTNCPX5NDNF43EVQW7C76/events.json","paper":"https://pith.science/paper/4JVJJNTN"},"agent_actions":{"view_html":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76","download_json":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76.json","view_paper":"https://pith.science/paper/4JVJJNTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.01714&json=true","fetch_graph":"https://pith.science/api/pith-number/4JVJJNTNCPX5NDNF43EVQW7C76/graph.json","fetch_events":"https://pith.science/api/pith-number/4JVJJNTNCPX5NDNF43EVQW7C76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76/action/storage_attestation","attest_author":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76/action/author_attestation","sign_citation":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76/action/citation_signature","submit_replication":"https://pith.science/pith/4JVJJNTNCPX5NDNF43EVQW7C76/action/replication_record"}},"created_at":"2026-05-18T00:51:19.790670+00:00","updated_at":"2026-05-18T00:51:19.790670+00:00"}