{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LOPLPJIBOBV27ICVX3MNYSMOQT","short_pith_number":"pith:LOPLPJIB","schema_version":"1.0","canonical_sha256":"5b9eb7a501706bafa055bed8dc498e84dec7ac4d608adc75e7fedac35c6fcff7","source":{"kind":"arxiv","id":"2002.06165","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jonathan Le Roux, Leda Sar{\\i}, Niko Moritz, Takaaki Hori","submitted_at":"2020-02-14T18:31:31Z","abstract_excerpt":"We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the training data and reads relevant i-vectors from the memory through an attention mechanism. The resulting memory vector (M-vector) is concatenated to the acoustic features or to the hidden layer activations of an E2E neural network model. The E2E ASR system is based on the joint connectionist temporal classification and attention-based encoder-decoder architec"},"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":"2002.06165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-14T18:31:31Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"aafef7a54c6c4bef79f21401d17c50fc6f2def9eb981c50b8169493318709ca8","abstract_canon_sha256":"b37d70cbdf840b56b0bfcfc57dc0184a4605f321eb235b0adb68ffe38fb8a054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:50.761615Z","signature_b64":"7PpU0ZH+CPm2BOEx0E9KJACdXJwp2029AkgHbEGjgI5RbFWBOwhqv27CiIWLEhE9Wk135zunqnxpsrizj3JlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9eb7a501706bafa055bed8dc498e84dec7ac4d608adc75e7fedac35c6fcff7","last_reissued_at":"2026-07-05T00:40:50.761199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:50.761199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jonathan Le Roux, Leda Sar{\\i}, Niko Moritz, Takaaki Hori","submitted_at":"2020-02-14T18:31:31Z","abstract_excerpt":"We propose an unsupervised speaker adaptation method inspired by the neural Turing machine for end-to-end (E2E) automatic speech recognition (ASR). The proposed model contains a memory block that holds speaker i-vectors extracted from the training data and reads relevant i-vectors from the memory through an attention mechanism. The resulting memory vector (M-vector) is concatenated to the acoustic features or to the hidden layer activations of an E2E neural network model. The E2E ASR system is based on the joint connectionist temporal classification and attention-based encoder-decoder architec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06165","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/2002.06165/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":"2002.06165","created_at":"2026-07-05T00:40:50.761256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06165v1","created_at":"2026-07-05T00:40:50.761256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06165","created_at":"2026-07-05T00:40:50.761256+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOPLPJIBOBV2","created_at":"2026-07-05T00:40:50.761256+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOPLPJIBOBV27ICV","created_at":"2026-07-05T00:40:50.761256+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOPLPJIB","created_at":"2026-07-05T00:40:50.761256+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/LOPLPJIBOBV27ICVX3MNYSMOQT","json":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT.json","graph_json":"https://pith.science/api/pith-number/LOPLPJIBOBV27ICVX3MNYSMOQT/graph.json","events_json":"https://pith.science/api/pith-number/LOPLPJIBOBV27ICVX3MNYSMOQT/events.json","paper":"https://pith.science/paper/LOPLPJIB"},"agent_actions":{"view_html":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT","download_json":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT.json","view_paper":"https://pith.science/paper/LOPLPJIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06165&json=true","fetch_graph":"https://pith.science/api/pith-number/LOPLPJIBOBV27ICVX3MNYSMOQT/graph.json","fetch_events":"https://pith.science/api/pith-number/LOPLPJIBOBV27ICVX3MNYSMOQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT/action/storage_attestation","attest_author":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT/action/author_attestation","sign_citation":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT/action/citation_signature","submit_replication":"https://pith.science/pith/LOPLPJIBOBV27ICVX3MNYSMOQT/action/replication_record"}},"created_at":"2026-07-05T00:40:50.761256+00:00","updated_at":"2026-07-05T00:40:50.761256+00:00"}