{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5AZ7XQK4EGWZI2ESSE5KDF3MWC","short_pith_number":"pith:5AZ7XQK4","schema_version":"1.0","canonical_sha256":"e833fbc15c21ad946892913aa1976cb08d07aacc2599601276a69e7235f73c7c","source":{"kind":"arxiv","id":"2409.13582","version":1},"attestation_state":"computed","paper":{"title":"Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Brittany Morin, Cheol Jun Cho, David Baquirin, Gopala Anumanchipalli, Jet Vonk, Jiachen Lian, Jingwen Liu, Jinming Zhang, Maria Luisa Gorno Tempini, Xuanru Zhou, Zachary Miller, Zoe Ezzes, Zongli Ye","submitted_at":"2024-09-20T15:35:32Z","abstract_excerpt":"Speech dysfluency modeling is a task to detect dysfluencies in speech, such as repetition, block, insertion, replacement, and deletion. Most recent advancements treat this problem as a time-based object detection problem. In this work, we revisit this problem from a new perspective: tokenizing dysfluencies and modeling the detection problem as a token-based automatic speech recognition (ASR) problem. We propose rule-based speech and text dysfluency simulators and develop VCTK-token, and then develop a Whisper-like seq2seq architecture to build a new benchmark with decent performance. We also s"},"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":"2409.13582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T15:35:32Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"9b40e4f53377f7c48b579fdc5e43ed3570a9765e282812d07a491654a8bb574b","abstract_canon_sha256":"ce1101ea381e634b6edd72cf5e1f285cbafdd50472b13e6625deec8ea40f83b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:38.094423Z","signature_b64":"6c3SktRHbShMWaxqd8kGmkJNFl2KuNeyVBGHtMzFbsCFkZqI2Pgi9DaAFW8/HVaH/CNMR7xyO9A3b2HhyZ0aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e833fbc15c21ad946892913aa1976cb08d07aacc2599601276a69e7235f73c7c","last_reissued_at":"2026-07-05T09:09:38.093867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:38.093867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Brittany Morin, Cheol Jun Cho, David Baquirin, Gopala Anumanchipalli, Jet Vonk, Jiachen Lian, Jingwen Liu, Jinming Zhang, Maria Luisa Gorno Tempini, Xuanru Zhou, Zachary Miller, Zoe Ezzes, Zongli Ye","submitted_at":"2024-09-20T15:35:32Z","abstract_excerpt":"Speech dysfluency modeling is a task to detect dysfluencies in speech, such as repetition, block, insertion, replacement, and deletion. Most recent advancements treat this problem as a time-based object detection problem. In this work, we revisit this problem from a new perspective: tokenizing dysfluencies and modeling the detection problem as a token-based automatic speech recognition (ASR) problem. We propose rule-based speech and text dysfluency simulators and develop VCTK-token, and then develop a Whisper-like seq2seq architecture to build a new benchmark with decent performance. We also s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13582","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/2409.13582/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":"2409.13582","created_at":"2026-07-05T09:09:38.093928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13582v1","created_at":"2026-07-05T09:09:38.093928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13582","created_at":"2026-07-05T09:09:38.093928+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AZ7XQK4EGWZ","created_at":"2026-07-05T09:09:38.093928+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AZ7XQK4EGWZI2ES","created_at":"2026-07-05T09:09:38.093928+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AZ7XQK4","created_at":"2026-07-05T09:09:38.093928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16681","citing_title":"Revisiting Rule-Based Stuttering Detection: A Comprehensive Analysis of Interpretable Models for Clinical Applications","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC","json":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC.json","graph_json":"https://pith.science/api/pith-number/5AZ7XQK4EGWZI2ESSE5KDF3MWC/graph.json","events_json":"https://pith.science/api/pith-number/5AZ7XQK4EGWZI2ESSE5KDF3MWC/events.json","paper":"https://pith.science/paper/5AZ7XQK4"},"agent_actions":{"view_html":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC","download_json":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC.json","view_paper":"https://pith.science/paper/5AZ7XQK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13582&json=true","fetch_graph":"https://pith.science/api/pith-number/5AZ7XQK4EGWZI2ESSE5KDF3MWC/graph.json","fetch_events":"https://pith.science/api/pith-number/5AZ7XQK4EGWZI2ESSE5KDF3MWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC/action/storage_attestation","attest_author":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC/action/author_attestation","sign_citation":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC/action/citation_signature","submit_replication":"https://pith.science/pith/5AZ7XQK4EGWZI2ESSE5KDF3MWC/action/replication_record"}},"created_at":"2026-07-05T09:09:38.093928+00:00","updated_at":"2026-07-05T09:09:38.093928+00:00"}