{"total":198,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158,"area":null},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"area":null},{"id":"2506.04779","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","created":"2025-06-05","cited_by_count":103,"area":"lr"},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"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":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"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":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53,"area":null},{"id":"2405.00823","title":"WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting","created":"2024-05-01","cited_by_count":53,"area":"agents"},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2309.15800","title":"Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study","created":"2023-09-27","cited_by_count":42,"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":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"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":"2209.09900","title":"LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging","created":"2022-09-20","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2306.00452","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","created":"2023-06-01","cited_by_count":28,"area":null},{"id":"2203.15863","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22,"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":"2306.01942","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","created":"2023-06-02","cited_by_count":21,"area":null},{"id":"2507.12705","title":"AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation","created":"2025-07-17","cited_by_count":21,"area":null},{"id":"2202.13155","title":"Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models","created":"2022-02-26","cited_by_count":20,"area":null},{"id":"2306.03208","title":"NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20,"area":"ssm"},{"id":"2408.03900","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","created":"2024-08-07","cited_by_count":20,"area":null},{"id":"2410.09230","title":"Improving Semantic Understanding in Speech Language Models via Brain-tuning","created":"2024-10-11","cited_by_count":20,"area":null},{"id":"2104.11127","title":"Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network","created":"2021-04-22","cited_by_count":19,"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":"2308.10529","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","created":"2023-08-21","cited_by_count":18,"area":null},{"id":"2310.14623","title":"CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks","created":"2023-10-23","cited_by_count":18,"area":"lr"},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2308.14456","title":"Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads","created":"2023-08-28","cited_by_count":17,"area":null},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2207.13211","title":"A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog","created":"2022-07-26","cited_by_count":14,"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":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2406.02925","title":"Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","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":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"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":"2109.08890","title":"Towards Joint Intent Detection and Slot Filling via Higher-order Attention","created":"2021-09-18","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":"2210.00572","title":"Risk-graded Safety for Handling Medical Queries in Conversational AI","created":"2022-10-02","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":"2302.14036","title":"Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator","created":"2023-02-27","cited_by_count":11,"area":null},{"id":"2307.07421","title":"SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding","created":"2023-07-12","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":"2212.08704","title":"Speech Aware Dialog System Technology Challenge (DSTC11)","created":"2022-12-16","cited_by_count":10,"area":null},{"id":"2306.08502","title":"ITALIC: An Italian Intent Classification Dataset","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2410.06707","title":"Calibrating Verbalized Probabilities for Large Language Models","created":"2024-10-09","cited_by_count":10,"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":"2405.04296","title":"Open Implementation and Study of BEST-RQ for Speech Processing","created":"2024-05-07","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":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2604.22821","title":"Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use","created":"2026-04-17","cited_by_count":9,"area":"agents"},{"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":"2207.09514","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2401.02921","title":"Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2502.15919","title":"Mind the Gap! Static and Interactive Evaluations of Large Audio Models","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2212.08542","title":"Context-aware Fine-tuning of Self-supervised Speech Models","created":"2022-12-16","cited_by_count":7,"area":null},{"id":"2502.12900","title":"Soundwave: Less is More for Speech-Text Alignment in LLMs","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2505.22857","title":"NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2209.12944","title":"On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering","created":"2022-09-26","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":"2305.13794","title":"Personalized Predictive ASR for Latency Reduction in Voice Assistants","created":"2023-05-23","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":"2310.16609","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2311.11375","title":"ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","created":"2023-11-19","cited_by_count":6,"area":null},{"id":"2406.03199","title":"Bayesian WeakS-to-Strong from Text Classification to Generation","created":"2024-05-24","cited_by_count":6,"area":null},{"id":"2409.06372","title":"SpeechTaxi: On Multilingual Semantic Speech Classification","created":"2024-09-10","cited_by_count":6,"area":null},{"id":"2507.22934","title":"Deep Learning Approaches for Multimodal Intent Recognition: A Survey","created":"2025-07-24","cited_by_count":6,"area":null},{"id":"2509.12093","title":"SENSE models: an open source solution for multilingual and multimodal semantic-based tasks","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2509.15389","title":"Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Data","created":"2025-09-18","cited_by_count":6,"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":"2211.08161","title":"An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding","created":"2022-11-15","cited_by_count":5,"area":"distill"},{"id":"2304.12810","title":"Transcending the \"Male Code\": Implicit Masculine Biases in NLP Contexts","created":"2023-04-22","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":"2305.12793","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2309.10707","title":"Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2501.12332","title":"Automatic Labelling with Open-source LLMs using Dynamic Label Schema Integration","created":"2025-01-21","cited_by_count":5,"area":null},{"id":"2505.15700","title":"\"Alexa, can you forget me?\" Machine Unlearning Benchmark in Spoken Language Understanding","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2205.00693","title":"Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2205.12818","title":"On Building Spoken Language Understanding Systems for Low Resourced Languages","created":"2022-05-25","cited_by_count":4,"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":"2304.13292","title":"Zero-Shot Slot and Intent Detection in Low-Resource Languages","created":"2023-04-26","cited_by_count":4,"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}],"next_cursor":"100"}