{"total":182,"rows":[{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"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":"2110.06848","title":"Decoupled Contrastive Learning","created":"2021-10-13","cited_by_count":143,"area":null},{"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":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"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":"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":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","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":"2306.00452","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","created":"2023-06-01","cited_by_count":28,"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":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2110.03876","title":"Phone-to-audio alignment without text: A Semi-supervised Approach","created":"2021-10-08","cited_by_count":26,"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":"2101.04792","title":"Learning Efficient Representations for Keyword Spotting with Triplet Loss","created":"2021-01-12","cited_by_count":24,"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":"2306.06672","title":"Reducing Barriers to Self-Supervised Learning: HuBERT Pre-training with Academic Compute","created":"2023-06-11","cited_by_count":21,"area":null},{"id":"2110.07957","title":"Don't speak too fast: The impact of data bias on self-supervised speech models","created":"2021-10-15","cited_by_count":20,"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":"2203.16773","title":"SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks","created":"2022-03-31","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":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","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":"2203.16104","title":"Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation","created":"2022-03-30","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":"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":"2207.13703","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","created":"2022-07-27","cited_by_count":14,"area":null},{"id":"2107.14203","title":"Did the Model Change? Efficiently Assessing Machine Learning API Shifts","created":"2021-07-29","cited_by_count":13,"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":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12,"area":null},{"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":"2106.15065","title":"Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding","created":"2021-06-29","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":"2306.08502","title":"ITALIC: An Italian Intent Classification Dataset","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2307.05862","title":"Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes","created":"2023-07-12","cited_by_count":10,"area":null},{"id":"2312.09665","title":"FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2506.11350","title":"GLAP: General contrastive audio-text pretraining across domains and languages","created":"2025-06-12","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":"2108.13048","title":"ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding","created":"2021-08-30","cited_by_count":9,"area":null},{"id":"2210.15283","title":"On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2211.17223","title":"Topological Data Analysis for Speech Processing","created":"2022-11-30","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":"2406.14686","title":"A Contrastive Learning Approach to Mitigate Bias in Speech Models","created":"2024-06-20","cited_by_count":9,"area":null},{"id":"2103.13610","title":"An Approach to Improve Robustness of NLP Systems against ASR Errors","created":"2021-03-25","cited_by_count":8,"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":"2207.06670","title":"Two-Pass Low Latency End-to-End Spoken Language Understanding","created":"2022-07-14","cited_by_count":8,"area":null},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","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":"2212.08542","title":"Context-aware Fine-tuning of Self-supervised Speech Models","created":"2022-12-16","cited_by_count":7,"area":null},{"id":"2306.08920","title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2309.07733","title":"Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features","created":"2023-09-14","cited_by_count":7,"area":null},{"id":"2311.09117","title":"R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces","created":"2023-11-15","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":"2111.04330","title":"Characterizing the adversarial vulnerability of speech self-supervised learning","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2206.14318","title":"Bottleneck Low-rank Transformers for Low-resource Spoken Language Understanding","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2409.18680","title":"Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models","created":"2024-09-27","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":"2109.02823","title":"Learning Visual-Audio Representations for Voice-Controlled Robots","created":"2021-09-07","cited_by_count":5,"area":null},{"id":"2111.14842","title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2112.06743","title":"Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2208.09708","title":"DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2303.03267","title":"Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding","created":"2023-03-02","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":"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":"2310.16318","title":"Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2104.01287","title":"Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems","created":"2021-04-03","cited_by_count":4,"area":null},{"id":"2110.09930","title":"Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning","created":"2021-10-18","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":"2305.14546","title":"On the Transferability of Whisper-based Representations for \"In-the-Wild\" Cross-Task Downstream Speech Applications","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2404.14415","title":"Domain Adaptation in Intent Classification Systems: A Review","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2410.03798","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2410.13179","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","created":"2024-10-17","cited_by_count":4,"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":"2207.00352","title":"Toward Low-Cost End-to-End Spoken Language Understanding","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2207.08179","title":"End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting","created":"2022-07-17","cited_by_count":3,"area":null},{"id":"2211.08402","title":"Introducing Semantics into Speech Encoders","created":"2022-11-15","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":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2304.07842","title":"A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers","created":"2023-04-16","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}],"next_cursor":"100"}