{"total":21,"rows":[{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2109.03381","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering","created":"2021-09-08","cited_by_count":39,"area":null},{"id":"2109.12072","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2204.14272","title":"End-to-end Spoken Conversational Question Answering: Task, Dataset and Model","created":"2022-04-29","cited_by_count":37,"area":null},{"id":"2106.02182","title":"Self-supervised Dialogue Learning for Spoken Conversational Question Answering","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2102.08345","title":"NoiseQA: Challenge Set Evaluation for User-Centric Question Answering","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2304.13689","title":"HeySQuAD: A Spoken Question Answering Dataset","created":"2023-04-26","cited_by_count":16,"area":null},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15,"area":null},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2308.10390","title":"LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models","created":"2023-08-20","cited_by_count":14,"area":null},{"id":"2401.13463","title":"SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering","created":"2024-01-24","cited_by_count":12,"area":null},{"id":"2209.00277","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","created":"2022-09-01","cited_by_count":5,"area":null},{"id":"2307.07057","title":"Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling","created":"2023-07-13","cited_by_count":3,"area":null},{"id":"2212.03866","title":"Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task","created":"2022-12-07","cited_by_count":2,"area":null},{"id":"2511.09282","title":"End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2107.04691","title":"An Initial Investigation of Non-Native Spoken Question-Answering","created":"2021-07-09","cited_by_count":1,"area":null},{"id":"2505.23308","title":"Spoken question answering for visual queries","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2505.19429","title":"Rhapsody: A Dataset for Highlight Detection in Podcasts","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22872","title":"Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}