{"total":35,"rows":[{"id":"2111.10367","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","created":"2021-11-19","cited_by_count":72,"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":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26,"area":null},{"id":"2202.08533","title":"AISHELL-NER: Named Entity Recognition from Chinese Speech","created":"2022-02-17","cited_by_count":19,"area":null},{"id":"2110.07592","title":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2305.12839","title":"CopyNE: Better Contextual ASR by Copying Named Entities","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2112.07648","title":"On the Use of External Data for Spoken Named Entity Recognition","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2109.07439","title":"Is \"moby dick\" a Whale or a Bird? Named Entities and Terminology in Speech Translation","created":"2021-09-15","cited_by_count":11,"area":null},{"id":"2203.16965","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","created":"2022-03-31","cited_by_count":11,"area":null},{"id":"2407.04533","title":"Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect","created":"2024-07-05","cited_by_count":7,"area":null},{"id":"2105.04719","title":"Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech","created":"2021-05-10","cited_by_count":6,"area":null},{"id":"2401.11382","title":"Using Large Language Model for End-to-End Chinese ASR and NER","created":"2024-01-21","cited_by_count":6,"area":null},{"id":"2210.11987","title":"Joint Speech Translation and Named Entity Recognition","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2303.10160","title":"Visual Information Matters for ASR Error Correction","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2306.08588","title":"Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation","created":"2023-06-14","cited_by_count":2,"area":null},{"id":"2407.04444","title":"TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2412.19102","title":"\"I've Heard of You!\": Generate Spoken Named Entity Recognition Data for Unseen Entities","created":"2024-12-26","cited_by_count":2,"area":null},{"id":"2406.13337","title":"Medical Spoken Named Entity Recognition","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2408.04174","title":"wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech","created":"2024-08-08","cited_by_count":1,"area":null},{"id":"2506.11064","title":"PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2509.03829","title":"NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2509.04473","title":"SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2204.09227","title":"Cross-stitched Multi-modal Encoders","created":"2022-04-20","cited_by_count":0,"area":null},{"id":"2210.17122","title":"Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2302.10186","title":"E2E Spoken Entity Extraction for Virtual Agents","created":"2023-02-16","cited_by_count":0,"area":null},{"id":"2307.01310","title":"Leveraging Cross-Lingual Transfer Learning in Spoken Named Entity Recognition Systems","created":"2023-07-03","cited_by_count":0,"area":null},{"id":"2309.07413","title":"CPPF: A contextual and post-processing-free model for automatic speech recognition","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2412.09045","title":"Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2501.07329","title":"Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2507.12951","title":"UniSLU: Unified Spoken Language Understanding from Heterogeneous Cross-Task Datasets","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.13376","title":"Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2508.19856","title":"TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2508.20700","title":"Generative Annotation for ASR Named Entity Correction","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.04357","title":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2604.02209","title":"CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech","created":"2026-04-02","cited_by_count":0,"area":null}],"next_cursor":null}