{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L33PU7T2IMYOKVLUNE6CY6QH2S","short_pith_number":"pith:L33PU7T2","schema_version":"1.0","canonical_sha256":"5ef6fa7e7a4330e55574693c2c7a07d4ae0905cf3db9e49be81948877d4929f0","source":{"kind":"arxiv","id":"2503.08533","version":1},"attestation_state":"computed","paper":{"title":"ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Jiatong Shi, Jinchuan Tian, Shikhar Bharadwaj, Shinji Watanabe, Shuichiro Shimizu, Siddhant Arora, Vaibhav Srivastav, William Chen, Yifan Peng, Yosuke Kashiwagi","submitted_at":"2025-03-11T15:24:02Z","abstract_excerpt":"Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. Motivated by this, we introduce an open-source, user-friendly toolkit designed to build unified web interfaces for various cascaded and E2E spoken dialogue systems. Our demo further provides users with the option to get on-the-fly automated evaluation metrics such as (1) latency, (2) ability to understand user input, (3) coherence, diversity, and relevance of system response, a"},"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":"2503.08533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T15:24:02Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9818acc7ee65be87e23422d8d33bf8e0cd5c7f3ac02d59f82ab64a5851df4748","abstract_canon_sha256":"52e330f2de0851ade7ed80c8578fc62fd5ce9181a92fcf2a65e6f62b16636b30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:01.671743Z","signature_b64":"sO0ACHIfhS3ywbTWo6UTw88YNUCrJDScSqwlpq5bYuzbpA5gTebp2Xv7gSq3R7HLt3CErxSdwuraJOlnZb5BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ef6fa7e7a4330e55574693c2c7a07d4ae0905cf3db9e49be81948877d4929f0","last_reissued_at":"2026-07-05T10:29:01.671287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:01.671287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Jiatong Shi, Jinchuan Tian, Shikhar Bharadwaj, Shinji Watanabe, Shuichiro Shimizu, Siddhant Arora, Vaibhav Srivastav, William Chen, Yifan Peng, Yosuke Kashiwagi","submitted_at":"2025-03-11T15:24:02Z","abstract_excerpt":"Advancements in audio foundation models (FMs) have fueled interest in end-to-end (E2E) spoken dialogue systems, but different web interfaces for each system makes it challenging to compare and contrast them effectively. Motivated by this, we introduce an open-source, user-friendly toolkit designed to build unified web interfaces for various cascaded and E2E spoken dialogue systems. Our demo further provides users with the option to get on-the-fly automated evaluation metrics such as (1) latency, (2) ability to understand user input, (3) coherence, diversity, and relevance of system response, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08533","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/2503.08533/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":"2503.08533","created_at":"2026-07-05T10:29:01.671354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08533v1","created_at":"2026-07-05T10:29:01.671354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08533","created_at":"2026-07-05T10:29:01.671354+00:00"},{"alias_kind":"pith_short_12","alias_value":"L33PU7T2IMYO","created_at":"2026-07-05T10:29:01.671354+00:00"},{"alias_kind":"pith_short_16","alias_value":"L33PU7T2IMYOKVLU","created_at":"2026-07-05T10:29:01.671354+00:00"},{"alias_kind":"pith_short_8","alias_value":"L33PU7T2","created_at":"2026-07-05T10:29:01.671354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23049","citing_title":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S","json":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S.json","graph_json":"https://pith.science/api/pith-number/L33PU7T2IMYOKVLUNE6CY6QH2S/graph.json","events_json":"https://pith.science/api/pith-number/L33PU7T2IMYOKVLUNE6CY6QH2S/events.json","paper":"https://pith.science/paper/L33PU7T2"},"agent_actions":{"view_html":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S","download_json":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S.json","view_paper":"https://pith.science/paper/L33PU7T2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08533&json=true","fetch_graph":"https://pith.science/api/pith-number/L33PU7T2IMYOKVLUNE6CY6QH2S/graph.json","fetch_events":"https://pith.science/api/pith-number/L33PU7T2IMYOKVLUNE6CY6QH2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S/action/storage_attestation","attest_author":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S/action/author_attestation","sign_citation":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S/action/citation_signature","submit_replication":"https://pith.science/pith/L33PU7T2IMYOKVLUNE6CY6QH2S/action/replication_record"}},"created_at":"2026-07-05T10:29:01.671354+00:00","updated_at":"2026-07-05T10:29:01.671354+00:00"}