{"total":20,"rows":[{"id":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"area":null},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","cited_by_count":35,"area":null},{"id":"2305.11073","title":"A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2305.18096","title":"Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2305.01620","title":"A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2305.08067","title":"Improving End-to-End SLU performance with Prosodic Attention and Distillation","created":"2023-05-14","cited_by_count":5,"area":null},{"id":"2212.13015","title":"Skit-S2I: An Indian Accented Speech to Intent dataset","created":"2022-12-26","cited_by_count":4,"area":null},{"id":"2506.07510","title":"DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2307.11005","title":"Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2307.12134","title":"Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2309.09390","title":"Augmenting text for spoken language understanding with Large Language Models","created":"2023-09-17","cited_by_count":2,"area":null},{"id":"2305.01194","title":"The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge","created":"2023-05-02","cited_by_count":1,"area":null},{"id":"2310.05374","title":"Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2406.06438","title":"Multimodal Contextualized Semantic Parsing from Speech","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2406.07823","title":"PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2406.13269","title":"Investigating Low-Cost LLM Annotation for~Spoken Dialogue Understanding Datasets","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2604.26500","title":"StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2608.22908","title":"Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}