{"work":{"id":"8553d8cf-0da9-40b7-a402-7c170c79df4b","openalex_id":"https://openalex.org/W4416114359","doi":"10.48550/arxiv.2503.04721","arxiv_id":"2503.04721","raw_key":null,"title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","authors":null,"authors_text":"Guan-Ting Lin, Jiachen Lian, Tingle Li, Qirui Wang, Gopala Anumanchipalli, Alexander H Liu, and Hung-yi Lee","year":2025,"venue":"cs.CL","abstract":"Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-processing one turn at a time - emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural conversations. However, current evaluations remain limited, focusing mainly on turn-based metrics or coarse corpus-level analyses. To address this, we introduce Full-Duplex-Bench, a benchmark that systematically evaluates key interactive behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent, reproducible assessment and provides a fair, fast evaluation setup. By releasing our benchmark and code, we aim to advance spoken dialogue modeling and foster the development of more natural and engaging SDMs.","external_url":"https://arxiv.org/abs/2503.04721","cited_by_count":0,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2503.04721","created_at":"2026-05-11T07:35:58.698615+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"In2024 IEEE Spo- ken Language Technology Workshop (SLT), pages 1115–1122","render_title":"In2024 IEEE Spo- ken Language Technology Workshop (SLT), pages 1115–1122"},"hub":{"state":{"work_id":"8553d8cf-0da9-40b7-a402-7c170c79df4b","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":26,"external_cited_by_count":0,"distinct_field_count":6,"first_pith_cited_at":"2025-05-21T19:17:29+00:00","last_pith_cited_at":"2026-07-08T23:24:55+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-09T19:29:29.306364+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}