{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HMZJFMFEB7NNCT34ILSWXKXKYJ","short_pith_number":"pith:HMZJFMFE","schema_version":"1.0","canonical_sha256":"3b3292b0a40fdad14f7c42e56baaeac243e288438671578827a6648ecad539f4","source":{"kind":"arxiv","id":"2307.09871","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Jingru Lin, Junyi Ao, Xianghu Yue","submitted_at":"2023-07-19T10:03:08Z","abstract_excerpt":"Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a novel self-supervised method to learn robust AWEs from a large-scale unlabelled speech corpus. Our model, named Correspondence Transformer Encoder (CTE), employs a teacher-student learning framework. We train the model based on the idea that different realisations of the same word should be close in the underlying embedding space. Specifically, we feed the tea"},"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":"2307.09871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-07-19T10:03:08Z","cross_cats_sorted":[],"title_canon_sha256":"d7e2abf1f9845e5658bb76cba94f17189ce75d5054327fdf7f5a05209f7ca549","abstract_canon_sha256":"2879468dd111e711e14bc52fac9f603aba256cf2bdfe69947561e9c969673380"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:47.440886Z","signature_b64":"4WBQPG7Sb4kU/41HJz3srTt96EQIo0oDbxF0ZtfVXG619gK7R9J+Nc4BFLhXlRTS2J5aDTsi+/Xk/VFJSJ1dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b3292b0a40fdad14f7c42e56baaeac243e288438671578827a6648ecad539f4","last_reissued_at":"2026-07-05T06:32:47.440475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:47.440475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Jingru Lin, Junyi Ao, Xianghu Yue","submitted_at":"2023-07-19T10:03:08Z","abstract_excerpt":"Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a novel self-supervised method to learn robust AWEs from a large-scale unlabelled speech corpus. Our model, named Correspondence Transformer Encoder (CTE), employs a teacher-student learning framework. We train the model based on the idea that different realisations of the same word should be close in the underlying embedding space. Specifically, we feed the tea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09871","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/2307.09871/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":"2307.09871","created_at":"2026-07-05T06:32:47.440532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.09871v1","created_at":"2026-07-05T06:32:47.440532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09871","created_at":"2026-07-05T06:32:47.440532+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMZJFMFEB7NN","created_at":"2026-07-05T06:32:47.440532+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMZJFMFEB7NNCT34","created_at":"2026-07-05T06:32:47.440532+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMZJFMFE","created_at":"2026-07-05T06:32:47.440532+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/HMZJFMFEB7NNCT34ILSWXKXKYJ","json":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ.json","graph_json":"https://pith.science/api/pith-number/HMZJFMFEB7NNCT34ILSWXKXKYJ/graph.json","events_json":"https://pith.science/api/pith-number/HMZJFMFEB7NNCT34ILSWXKXKYJ/events.json","paper":"https://pith.science/paper/HMZJFMFE"},"agent_actions":{"view_html":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ","download_json":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ.json","view_paper":"https://pith.science/paper/HMZJFMFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.09871&json=true","fetch_graph":"https://pith.science/api/pith-number/HMZJFMFEB7NNCT34ILSWXKXKYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HMZJFMFEB7NNCT34ILSWXKXKYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ/action/storage_attestation","attest_author":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ/action/author_attestation","sign_citation":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ/action/citation_signature","submit_replication":"https://pith.science/pith/HMZJFMFEB7NNCT34ILSWXKXKYJ/action/replication_record"}},"created_at":"2026-07-05T06:32:47.440532+00:00","updated_at":"2026-07-05T06:32:47.440532+00:00"}