{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KYLHX6JKT3PBFXYHSTSTJDOT7T","short_pith_number":"pith:KYLHX6JK","schema_version":"1.0","canonical_sha256":"56167bf92a9ede12df0794e5348dd3fce8effe0cfb791f07bb2a6787fc764818","source":{"kind":"arxiv","id":"1602.00426","version":1},"attestation_state":"computed","paper":{"title":"An Iterative Deep Learning Framework for Unsupervised Discovery of Speech Features and Linguistic Units with Applications on Spoken Term Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng-Tao Chung, Cheng-Yu Tsai, Chia-Hsiang Liu, Hsiang-Hung Lu, Hung-yi Lee, Lin-shan Lee","submitted_at":"2016-02-01T08:37:56Z","abstract_excerpt":"In this work we aim to discover high quality speech features and linguistic units directly from unlabeled speech data in a zero resource scenario. The results are evaluated using the metrics and corpora proposed in the Zero Resource Speech Challenge organized at Interspeech 2015. A Multi-layered Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets of acoustic tokens from the given corpus. Each acoustic token set is specified by a set of hyperparameters that describe the model configuration. These sets of acoustic tokens carry different characteristics fof the given co"},"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":"1602.00426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-01T08:37:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"450b4cb56898a6ae237871f6b56d452baa92b6d70921eedc005250f1f7e7cfb1","abstract_canon_sha256":"6749f5df612d58f7cd5a518eb3b8ace32685af0ccf8cee357fa580175f7a0376"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:35.395000Z","signature_b64":"bCLYYLdTDaMUg4f9TF3JjtaItH6fkWRVm7pdmvtX24GqjoMcC3igrmyFRba77zxMk9cGSQgdEBY05HkWufsqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56167bf92a9ede12df0794e5348dd3fce8effe0cfb791f07bb2a6787fc764818","last_reissued_at":"2026-05-18T01:21:35.394509Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:35.394509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Iterative Deep Learning Framework for Unsupervised Discovery of Speech Features and Linguistic Units with Applications on Spoken Term Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheng-Tao Chung, Cheng-Yu Tsai, Chia-Hsiang Liu, Hsiang-Hung Lu, Hung-yi Lee, Lin-shan Lee","submitted_at":"2016-02-01T08:37:56Z","abstract_excerpt":"In this work we aim to discover high quality speech features and linguistic units directly from unlabeled speech data in a zero resource scenario. The results are evaluated using the metrics and corpora proposed in the Zero Resource Speech Challenge organized at Interspeech 2015. A Multi-layered Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets of acoustic tokens from the given corpus. Each acoustic token set is specified by a set of hyperparameters that describe the model configuration. These sets of acoustic tokens carry different characteristics fof the given co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.00426","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":"1602.00426","created_at":"2026-05-18T01:21:35.394601+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.00426v1","created_at":"2026-05-18T01:21:35.394601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.00426","created_at":"2026-05-18T01:21:35.394601+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYLHX6JKT3PB","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYLHX6JKT3PBFXYH","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYLHX6JK","created_at":"2026-05-18T12:30:29.479603+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/KYLHX6JKT3PBFXYHSTSTJDOT7T","json":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T.json","graph_json":"https://pith.science/api/pith-number/KYLHX6JKT3PBFXYHSTSTJDOT7T/graph.json","events_json":"https://pith.science/api/pith-number/KYLHX6JKT3PBFXYHSTSTJDOT7T/events.json","paper":"https://pith.science/paper/KYLHX6JK"},"agent_actions":{"view_html":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T","download_json":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T.json","view_paper":"https://pith.science/paper/KYLHX6JK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.00426&json=true","fetch_graph":"https://pith.science/api/pith-number/KYLHX6JKT3PBFXYHSTSTJDOT7T/graph.json","fetch_events":"https://pith.science/api/pith-number/KYLHX6JKT3PBFXYHSTSTJDOT7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T/action/storage_attestation","attest_author":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T/action/author_attestation","sign_citation":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T/action/citation_signature","submit_replication":"https://pith.science/pith/KYLHX6JKT3PBFXYHSTSTJDOT7T/action/replication_record"}},"created_at":"2026-05-18T01:21:35.394601+00:00","updated_at":"2026-05-18T01:21:35.394601+00:00"}