{"total":47,"rows":[{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91,"area":null},{"id":"2304.06795","title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","created":"2023-04-13","cited_by_count":58,"area":null},{"id":"2309.02285","title":"PromptTTS 2: Describing and Generating Voices with Text Prompt","created":"2023-09-05","cited_by_count":48,"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":"2205.08180","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","created":"2022-05-17","cited_by_count":32,"area":null},{"id":"2302.14132","title":"Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding","created":"2023-02-27","cited_by_count":31,"area":null},{"id":"2305.13512","title":"Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding","created":"2023-05-22","cited_by_count":21,"area":null},{"id":"2211.05869","title":"A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding","created":"2022-11-10","cited_by_count":18,"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":"2204.08920","title":"Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation","created":"2022-04-19","cited_by_count":11,"area":null},{"id":"2210.16663","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2210.15734","title":"Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models","created":"2022-10-27","cited_by_count":10,"area":null},{"id":"2310.05513","title":"Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond","created":"2023-10-09","cited_by_count":10,"area":null},{"id":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","cited_by_count":9,"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":"2404.08857","title":"Voice Attribute Editing with Text Prompt","created":"2024-04-13","cited_by_count":9,"area":null},{"id":"2406.10083","title":"On the Evaluation of Speech Foundation Models for Spoken Language Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2207.06670","title":"Two-Pass Low Latency End-to-End Spoken Language Understanding","created":"2022-07-14","cited_by_count":8,"area":null},{"id":"2207.11964","title":"ConceptBeam: Concept Driven Target Speech Extraction","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2210.16554","title":"End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator","created":"2022-10-29","cited_by_count":6,"area":null},{"id":"2211.08726","title":"Streaming Joint Speech Recognition and Disfluency Detection","created":"2022-11-16","cited_by_count":6,"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":"2305.09652","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3,"area":null},{"id":"2211.13703","title":"Multitask Learning for Low Resource Spoken Language Understanding","created":"2022-11-24","cited_by_count":3,"area":null},{"id":"2305.00926","title":"Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History","created":"2023-05-01","cited_by_count":3,"area":null},{"id":"2305.17499","title":"CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2307.01764","title":"Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data","created":"2023-07-04","cited_by_count":3,"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":"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":"2406.12317","title":"Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2408.06043","title":"Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning","created":"2024-08-12","cited_by_count":2,"area":null},{"id":"2505.07731","title":"Spoken Language Understanding on Unseen Tasks With In-Context Learning","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2310.06103","title":"Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2310.14429","title":"Text generation for dataset augmentation in security classification tasks","created":"2023-10-22","cited_by_count":1,"area":null},{"id":"2312.11142","title":"Efficiency-oriented approaches for self-supervised speech representation learning","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2603.21478","title":"TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild","created":"2026-03-23","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":"2305.02937","title":"End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2310.02699","title":"Continual Contrastive Spoken Language Understanding","created":"2023-10-04","cited_by_count":0,"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":"2403.15510","title":"Privacy-Preserving End-to-End Spoken Language Understanding","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2406.14747","title":"An Adapter-Based Unified Model for Multiple Spoken Language Processing Tasks","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2409.09506","title":"ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration","created":"2024-09-14","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}],"next_cursor":null}