{"url":"/task/spoken-dialogue-systems","name":"Spoken Dialogue Systems","slug":"spoken-dialogue-systems","description_markdown":null,"categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":254,"papers_with_code":26,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/dialogue-state-tracking-challenge","name":"Dialogue State Tracking Challenge","full_name":"Dialogue State Tracking Challenge","num_papers_in_archive":33},{"url":"/dataset/sd-eval","name":"SD-Eval","full_name":"","num_papers_in_archive":9},{"url":"/dataset/cqr","name":"CQR","full_name":"Contextual Query Rewrite","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":26,"of":26,"tagged_in_all":254,"items":[{"url":"/paper/plato-dialogue-system-a-flexible","title":"Plato Dialogue System: A Flexible Conversational AI Research Platform","date":"2020-01-17","arxiv_id":"2001.06463","repositories_listed":4,"syntology":null},{"url":"/paper/slot-gated-modeling-for-joint-slot-filling","title":"Slot-Gated Modeling for Joint Slot Filling and Intent Prediction","date":"2018-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/semantically-conditioned-lstm-based-natural","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","date":"2015-08-07","arxiv_id":"1508.01745","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/wavreward-spoken-dialogue-models-with","title":"WavReward: Spoken Dialogue Models With Generalist Reward Evaluators","date":"2025-05-14","arxiv_id":"2505.09558","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-textless-dialogue-generation","title":"Real-Time Textless Dialogue Generation","date":"2025-01-08","arxiv_id":"2501.04877","repositories_listed":1,"syntology":null},{"url":"/paper/slam-omni-timbre-controllable-voice","title":"SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training","date":"2024-12-20","arxiv_id":"2412.15649","repositories_listed":1,"syntology":null},{"url":"/paper/wavchat-a-survey-of-spoken-dialogue-models","title":"WavChat: A Survey of Spoken Dialogue Models","date":"2024-11-15","arxiv_id":"2411.13577","repositories_listed":1,"syntology":null},{"url":"/paper/omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","repositories_listed":1,"syntology":null},{"url":"/paper/saslaw-dialogue-speech-corpus-with-audio","title":"SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis","date":"2024-08-13","arxiv_id":"2408.06858","repositories_listed":1,"syntology":null},{"url":"/paper/pslm-parallel-generation-of-text-and-speech","title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","date":"2024-06-18","arxiv_id":"2406.12428","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/towards-joint-modeling-of-dialogue-response","title":"Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model","date":"2023-09-20","arxiv_id":"2309.11000","repositories_listed":1,"syntology":null},{"url":"/paper/olisia-a-cascade-system-for-spoken-dialogue","title":"OLISIA: a Cascade System for Spoken Dialogue State Tracking","date":"2023-04-20","arxiv_id":"2304.11073","repositories_listed":1,"syntology":null},{"url":"/paper/when-can-i-speak-predicting-initiation-points","title":"When can I Speak? Predicting initiation points for spoken dialogue agents","date":"2022-08-07","arxiv_id":"2208.03812","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/evi-multilingual-spoken-dialogue-tasks-and-1","title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","date":"2022-04-28","arxiv_id":"2204.13496","repositories_listed":1,"syntology":null},{"url":"/paper/how-robust-r-u-evaluating-task-oriented","title":"\"How Robust r u?\": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations","date":"2021-09-28","arxiv_id":"2109.13489","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-asr-ambiguity-for-dialogue-state","title":"Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks","date":"2020-02-03","arxiv_id":"2002.00768","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-multi-task-natural-language","title":"Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU","date":"2019-10-02","arxiv_id":"1910.00912","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/a-dataset-for-resolving-referring-expressions","title":"A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR)","date":"2019-03-28","arxiv_id":"1903.11783","repositories_listed":1,"syntology":null},{"url":"/paper/variational-cross-domain-natural-language","title":"Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems","date":"2018-12-20","arxiv_id":"1812.08879","repositories_listed":1,"syntology":null},{"url":"/paper/findings-of-the-e2e-nlg-challenge","title":"Findings of the E2E NLG Challenge","date":"2018-10-02","arxiv_id":"1810.01170","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-generation-by-hierarchical","title":"Natural Language Generation by Hierarchical Decoding with Linguistic Patterns","date":"2018-08-08","arxiv_id":"1808.02747","repositories_listed":1,"syntology":null},{"url":"/paper/how-time-matters-learning-time-decay","title":"How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-learning-transferable-conversational","title":"Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling","date":"2018-03-31","arxiv_id":"1804.00146","repositories_listed":1,"syntology":null},{"url":"/paper/a-context-aware-natural-language-generator-1","title":"A Context-aware Natural Language Generator for Dialogue Systems","date":"2016-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-context-aware-natural-language-generator","title":"A Context-aware Natural Language Generator for Dialogue Systems","date":"2016-08-25","arxiv_id":"1608.07076","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-to-sequence-generation-for-spoken-1","title":"Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}