{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K7AQJVC4JZTK7VJS2MQY56DPCN","short_pith_number":"pith:K7AQJVC4","schema_version":"1.0","canonical_sha256":"57c104d45c4e66afd532d3218ef86f1366fb8e47c4139ddad29bbc9fa328d8b8","source":{"kind":"arxiv","id":"2505.19774","version":1},"attestation_state":"computed","paper":{"title":"DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Akshat Jaiswal, Debmalya Chakrabarty, Frederick Weber, Harish Arsikere, K V Vijay Girish, Nikhil Bhave, Prabash Reddy Male, Prakhar Swarup, Prantik Sen, Sambuddha Bhattacharya, Sri Garimella, Swayambhu Nath Ray","submitted_at":"2025-05-26T09:57:59Z","abstract_excerpt":"Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited exploration to effectively handle both streaming and non-streaming applications, while achieving state-of-the-art performance. We introduce DuRep, a Dual-mode Speech Representation learning setup, which enables a single speech encoder to function efficiently in both offline and online modes without additional parameters or mode-specific adjustments, across downs"},"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":"2505.19774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T09:57:59Z","cross_cats_sorted":[],"title_canon_sha256":"e8beb5b3ff37c06b1b6f98102717a318ac50fafafe57c19365bcd07bc5f4b45d","abstract_canon_sha256":"3349f8070c87a08e16b111d22b31989d7368423f21c4f17989fd675afa07bb78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:35.974898Z","signature_b64":"Zw/BK0rRBnHEzRMLqR/iQ+j74hRdPfwWxYGGBSDNrOcQn357r7VCf7ElZ978BQ7jjvhk0AJXy5pjGoCjnFl3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57c104d45c4e66afd532d3218ef86f1366fb8e47c4139ddad29bbc9fa328d8b8","last_reissued_at":"2026-07-05T11:09:35.974420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:35.974420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Akshat Jaiswal, Debmalya Chakrabarty, Frederick Weber, Harish Arsikere, K V Vijay Girish, Nikhil Bhave, Prabash Reddy Male, Prakhar Swarup, Prantik Sen, Sambuddha Bhattacharya, Sri Garimella, Swayambhu Nath Ray","submitted_at":"2025-05-26T09:57:59Z","abstract_excerpt":"Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited exploration to effectively handle both streaming and non-streaming applications, while achieving state-of-the-art performance. We introduce DuRep, a Dual-mode Speech Representation learning setup, which enables a single speech encoder to function efficiently in both offline and online modes without additional parameters or mode-specific adjustments, across downs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19774","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/2505.19774/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":"2505.19774","created_at":"2026-07-05T11:09:35.974471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19774v1","created_at":"2026-07-05T11:09:35.974471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19774","created_at":"2026-07-05T11:09:35.974471+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7AQJVC4JZTK","created_at":"2026-07-05T11:09:35.974471+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7AQJVC4JZTK7VJS","created_at":"2026-07-05T11:09:35.974471+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7AQJVC4","created_at":"2026-07-05T11:09:35.974471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13544","citing_title":"Adaptive Turn-Taking for Real-time Multi-Party Voice Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13544","citing_title":"Adaptive Turn-Taking for Real-time Multi-Party Voice Agents","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN","json":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN.json","graph_json":"https://pith.science/api/pith-number/K7AQJVC4JZTK7VJS2MQY56DPCN/graph.json","events_json":"https://pith.science/api/pith-number/K7AQJVC4JZTK7VJS2MQY56DPCN/events.json","paper":"https://pith.science/paper/K7AQJVC4"},"agent_actions":{"view_html":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN","download_json":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN.json","view_paper":"https://pith.science/paper/K7AQJVC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19774&json=true","fetch_graph":"https://pith.science/api/pith-number/K7AQJVC4JZTK7VJS2MQY56DPCN/graph.json","fetch_events":"https://pith.science/api/pith-number/K7AQJVC4JZTK7VJS2MQY56DPCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN/action/storage_attestation","attest_author":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN/action/author_attestation","sign_citation":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN/action/citation_signature","submit_replication":"https://pith.science/pith/K7AQJVC4JZTK7VJS2MQY56DPCN/action/replication_record"}},"created_at":"2026-07-05T11:09:35.974471+00:00","updated_at":"2026-07-05T11:09:35.974471+00:00"}