{"list":"other","total":80,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257},{"id":"2011.03088","title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification","created":"2020-11-05","cited_by_count":201},{"id":"1506.08909","title":"The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems","created":"2015-06-30","cited_by_count":172},{"id":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"2004.05773","title":"Generating Fact Checking Explanations","created":"2020-04-13","cited_by_count":132},{"id":"2004.08449","title":"Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills","created":"2020-04-17","cited_by_count":131},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"2205.12487","title":"End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models","created":"2022-05-25","cited_by_count":107},{"id":"1809.07358","title":"A Dataset for Document Grounded Conversations","created":"2018-09-19","cited_by_count":104},{"id":"2103.06410","title":"MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization","created":"2021-03-11","cited_by_count":104},{"id":"2111.09344","title":"The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage","created":"2021-11-17","cited_by_count":101},{"id":"2308.11995","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","created":"2023-08-23","cited_by_count":89},{"id":"2309.08105","title":"Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context","created":"2023-09-15","cited_by_count":85},{"id":"2104.04045","title":"End-to-end speaker segmentation for overlap-aware resegmentation","created":"2021-04-08","cited_by_count":80},{"id":"2104.02014","title":"SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition","created":"2021-04-05","cited_by_count":78},{"id":"2207.01063","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","created":"2022-07-03","cited_by_count":69},{"id":"2104.11348","title":"Earnings-21: A Practical Benchmark for ASR in the Wild","created":"2021-04-22","cited_by_count":62},{"id":"2110.08222","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","created":"2021-10-15","cited_by_count":62},{"id":"2310.15515","title":"Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation","created":"2023-10-24","cited_by_count":51},{"id":"2412.10510","title":"DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts","created":"2024-12-13","cited_by_count":43},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41},{"id":"2106.00829","title":"ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining","created":"2021-06-01","cited_by_count":38},{"id":"2310.09754","title":"EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification","created":"2023-10-15","cited_by_count":36},{"id":"2401.11969","title":"Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research","created":"2024-01-22","cited_by_count":35},{"id":"1909.13447","title":"DiPCo -- Dinner Party Corpus","created":"2019-09-30","cited_by_count":20},{"id":"2112.08544","title":"NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge","created":"2021-12-16","cited_by_count":20},{"id":"2210.04710","title":"Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter","created":"2022-10-10","cited_by_count":19},{"id":"2109.11292","title":"Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System","created":"2021-09-23","cited_by_count":18},{"id":"2212.01060","title":"Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning","created":"2022-12-02","cited_by_count":15},{"id":"2305.11355","title":"MD3: The Multi-Dialect Dataset of Dialogues","created":"2023-05-19","cited_by_count":13},{"id":"2310.06547","title":"Rationale-Enhanced Language Models are Better Continual Relation Learners","created":"2023-10-10","cited_by_count":13},{"id":"2505.18596","title":"Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models","created":"2025-05-24","cited_by_count":12},{"id":"2310.16746","title":"HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis","created":"2023-10-25","cited_by_count":10},{"id":"2112.00712","title":"STEM: Unsupervised STructural EMbedding for Stance Detection","created":"2021-12-01","cited_by_count":9},{"id":"2410.16148","title":"PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters","created":"2024-10-21","cited_by_count":8},{"id":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8},{"id":"1903.04484","title":"The Truth and Nothing but the Truth: Multimodal Analysis for Deception Detection","created":"2019-03-11","cited_by_count":7},{"id":"1910.01990","title":"Detecting Deception in Political Debates Using Acoustic and Textual Features","created":"2019-10-04","cited_by_count":7},{"id":"2302.12569","title":"Implicit Temporal Reasoning for Evidence-Based Fact-Checking","created":"2023-02-24","cited_by_count":7},{"id":"2306.05535","title":"Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data","created":"2023-05-24","cited_by_count":7},{"id":"2403.08890","title":"From \"um\" to \"yeah\": Producing, predicting, and regulating information flow in human conversation","created":"2024-03-13","cited_by_count":7},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7},{"id":"2502.13645","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","created":"2025-02-19","cited_by_count":7},{"id":"1504.04712","title":"Towards Detecting Rumours in Social Media","created":"2015-04-18","cited_by_count":6},{"id":"2406.12645","title":"Evaluating Evidence Attribution in Generated Fact Checking Explanations","created":"2024-06-18","cited_by_count":6},{"id":"2411.07892","title":"Mapping the Podcast Ecosystem with the Structured Podcast Research Corpus","created":"2024-11-12","cited_by_count":6},{"id":"2503.15124","title":"Evaluating ASR Confidence Scores for Automated Error Detection in User-Assisted Correction Interfaces","created":"2025-03-19","cited_by_count":6},{"id":"2311.08195","title":"Automated Fact-Checking in Dialogue: Are Specialized Models Needed?","created":"2023-11-14","cited_by_count":5},{"id":"2408.00292","title":"Everything We Hear: Towards Tackling Misinformation in Podcasts","created":"2024-08-01","cited_by_count":5},{"id":"2408.07448","title":"LiveFC: A System for Live Fact-Checking of Audio Streams","created":"2024-08-14","cited_by_count":5},{"id":"2408.12558","title":"Exploring the Role of Audio in Multimodal Misinformation Detection","created":"2024-08-22","cited_by_count":5},{"id":"2508.05554","title":"SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription","created":"2025-08-07","cited_by_count":5},{"id":"2501.12640","title":"Toxicity Begets Toxicity: Unraveling Conversational Chains in Political Podcasts","created":"2025-01-22","cited_by_count":4},{"id":"2506.00267","title":"CASPER: A Large Scale Spontaneous Speech Dataset","created":"2025-05-30","cited_by_count":4},{"id":"2506.00955","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","created":"2025-06-01","cited_by_count":4},{"id":"2507.00214","title":"Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning","created":"2025-06-30","cited_by_count":4},{"id":"2508.12186","title":"MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking","created":"2025-08-17","cited_by_count":4},{"id":"2104.07868","title":"Segmenting Subtitles for Correcting ASR Segmentation Errors","created":"2021-04-16","cited_by_count":3},{"id":"2504.12882","title":"ViClaim: A Multilingual Multilabel Dataset for Automatic Claim Detection in Videos","created":"2025-04-17","cited_by_count":3},{"id":"2506.15081","title":"Improving Dialogue Discourse Parsing through Discourse-aware Utterance Clarification","created":"2025-06-18","cited_by_count":3},{"id":"2203.15833","title":"Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture","created":"2022-03-29","cited_by_count":2},{"id":"2502.01402","title":"Annotation Tool and Dataset for Fact-Checking Podcasts","created":"2025-02-03","cited_by_count":2},{"id":"2509.15476","title":"Evaluating Multimodal Large Language Models on Spoken Sarcasm Understanding","created":"2025-09-18","cited_by_count":2},{"id":"2505.23207","title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","created":"2025-05-29","cited_by_count":1},{"id":"2506.20018","title":"Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models","created":"2025-06-24","cited_by_count":1}],"next_cursor":null}