{"total":63,"rows":[{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"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":"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":"2102.06283","title":"Speech-language Pre-training for End-to-end Spoken Language Understanding","created":"2021-02-11","cited_by_count":27,"area":null},{"id":"2105.00573","title":"Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks","created":"2021-05-02","cited_by_count":24,"area":null},{"id":"2207.10643","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","created":"2022-06-29","cited_by_count":22,"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":"2203.00006","title":"Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems","created":"2022-02-26","cited_by_count":20,"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":"2106.09009","title":"End-to-End Spoken Language Understanding for Generalized Voice Assistants","created":"2021-06-16","cited_by_count":17,"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":"2108.02598","title":"Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification","created":"2021-08-05","cited_by_count":14,"area":"distill"},{"id":"2102.07370","title":"Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11,"area":null},{"id":"2204.00803","title":"End-to-end model for named entity recognition from speech without paired training data","created":"2022-04-02","cited_by_count":11,"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":"2102.01013","title":"End2End Acoustic to Semantic Transduction","created":"2021-02-01","cited_by_count":10,"area":null},{"id":"2102.06750","title":"Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2106.06598","title":"Leveraging Pre-trained Language Model for Speech Sentiment Analysis","created":"2021-06-11","cited_by_count":9,"area":null},{"id":"2108.08405","title":"Integrating Dialog History into End-to-End Spoken Language Understanding Systems","created":"2021-08-18","cited_by_count":9,"area":null},{"id":"2104.05752","title":"Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2105.07071","title":"Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2105.10042","title":"A Streaming End-to-End Framework For Spoken Language Understanding","created":"2021-05-20","cited_by_count":8,"area":null},{"id":"2111.00400","title":"FANS: Fusing ASR and NLU for on-device SLU","created":"2021-10-31","cited_by_count":8,"area":null},{"id":"2204.01893","title":"Deliberation Model for On-Device Spoken Language Understanding","created":"2022-04-04","cited_by_count":8,"area":null},{"id":"2104.03842","title":"RNN Transducer Models For Spoken Language Understanding","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2106.04660","title":"Sequential End-to-End Intent and Slot Label Classification and Localization","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2210.05291","title":"On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2104.10357","title":"Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning","created":"2021-04-21","cited_by_count":6,"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":"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":"2106.15238","title":"Representation based meta-learning for few-shot spoken intent recognition","created":"2021-06-29","cited_by_count":5,"area":null},{"id":"2106.15919","title":"On joint training with interfaces for spoken language understanding","created":"2021-06-30","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":"2105.05582","title":"Discrete representations in neural models of spoken language","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2204.00558","title":"Multi-task RNN-T with Semantic Decoder for Streamable Spoken Language Understanding","created":"2022-04-01","cited_by_count":3,"area":null},{"id":"2204.03315","title":"Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model","created":"2022-04-07","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":"2305.17499","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":"2306.06819","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2311.18188","title":"Speech Understanding on Tiny Devices with A Learning Cache","created":"2023-11-30","cited_by_count":3,"area":null},{"id":"2211.07710","title":"End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2212.08489","title":"Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2307.01323","title":"Semantic enrichment towards efficient speech representations","created":"2023-07-03","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":"2312.00336","title":"Hypergraph Node Representation Learning with One-Stage Message Passing","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2109.13222","title":"Using Pause Information for More Accurate Entity Recognition","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2110.11769","title":"Clustering of Bank Customers using LSTM-based encoder-decoder and Dynamic Time Warping","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2205.11008","title":"Calibrate and Refine! A Novel and Agile Framework for ASR-error Robust Intent Detection","created":"2022-05-23","cited_by_count":1,"area":null},{"id":"2302.12369","title":"Factual Consistency Oriented Speech Recognition","created":"2023-02-24","cited_by_count":1,"area":null},{"id":"2406.12141","title":"A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2407.07425","title":"Out-of-distribution generalisation in spoken language understanding","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2109.13486","title":"Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification","created":"2021-09-28","cited_by_count":0,"area":"distill"},{"id":"2201.12105","title":"Improving End-to-End Models for Set Prediction in Spoken Language Understanding","created":"2022-01-28","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":"2303.06585","title":"Improving the Intent Classification accuracy in Noisy Environment","created":"2023-03-12","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":"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":"2309.02780","title":"GRASS: Unified Generation Model for Speech-to-Semantic Tasks","created":"2023-09-06","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":"2511.11000","title":"DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2603.16483","title":"On the Emotion Understanding of Synthesized Speech","created":"2026-03-17","cited_by_count":0,"area":null}],"next_cursor":null}