{"total":72,"rows":[{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158,"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":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","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":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42,"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":"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":"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":"2310.08715","title":"Toward Joint Language Modeling for Speech Units and Text","created":"2023-10-12","cited_by_count":28,"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":"2510.07293","title":"AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs","created":"2025-10-08","cited_by_count":22,"area":"inference"},{"id":"2406.16808","title":"Exploring the Capability of Mamba in Speech Applications","created":"2024-06-24","cited_by_count":20,"area":"ssm"},{"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":"2502.12414","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2409.04927","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","created":"2024-09-07","cited_by_count":16,"area":"lr"},{"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":"2508.18240","title":"MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols","created":"2025-08-22","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":"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":"2406.09345","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"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":"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":"2212.08542","title":"Context-aware Fine-tuning of Self-supervised Speech Models","created":"2022-12-16","cited_by_count":7,"area":null},{"id":"2309.00723","title":"Contextual Biasing of Named-Entities with Large Language Models","created":"2023-09-01","cited_by_count":7,"area":null},{"id":"2502.13645","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","created":"2025-02-19","cited_by_count":7,"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":"2409.06372","title":"SpeechTaxi: On Multilingual Semantic Speech Classification","created":"2024-09-10","cited_by_count":6,"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":"2211.00586","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2406.09618","title":"Multi-Modal Retrieval For Large Language Model Based Speech Recognition","created":"2024-06-13","cited_by_count":4,"area":"mllm"},{"id":"2512.10624","title":"AgriGPT-Omni: A Unified Speech-Vision-Text Framework for Multilingual Agricultural Intelligence","created":"2025-12-11","cited_by_count":4,"area":"mllm"},{"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":"2312.09895","title":"Generative Context-aware Fine-tuning of Self-supervised Speech Models","created":"2023-12-15","cited_by_count":3,"area":null},{"id":"2409.08107","title":"WhisperNER: Unified Open Named Entity and Speech Recognition","created":"2024-09-12","cited_by_count":3,"area":null},{"id":"2512.16832","title":"What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2305.12311","title":"i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data","created":"2023-05-21","cited_by_count":2,"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":"2405.11519","title":"MSNER: A Multilingual Speech Dataset for Named Entity Recognition","created":"2024-05-19","cited_by_count":2,"area":null},{"id":"2502.12408","title":"On the Robust Approximation of ASR Metrics","created":"2025-02-18","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":"2310.05919","title":"Few-Shot Spoken Language Understanding via Joint Speech-Text Models","created":"2023-10-09","cited_by_count":1,"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":"2402.05819","title":"Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2406.13337","title":"Medical Spoken Named Entity Recognition","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2409.06263","title":"Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2506.01133","title":"From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models","created":"2025-06-01","cited_by_count":1,"area":"lr"},{"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":"2511.01619","title":"ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2603.10827","title":"Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation","created":"2026-03-11","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":"2204.10461","title":"WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment","created":"2022-04-22","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":"2308.02903","title":"LaDA: Latent Dialogue Action For Zero-shot Cross-lingual Neural Network Language Modeling","created":"2023-08-05","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":"2404.17983","title":"TI-ASU: Toward Robust Automatic Speech Understanding through Text-to-speech Imputation Against Missing Speech Modality","created":"2024-04-27","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":"2412.14087","title":"SEKE: Specialised Experts for Keyword Extraction","created":"2024-12-18","cited_by_count":0,"area":"moe"},{"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":"2609.00330","title":"Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.13602","title":"$\\tau$-Elicitation: Benchmarking multi-turn entity extraction in voice agents","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.33204","title":"Turning Speech Language Models into Multilingual Listeners","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.08831","title":"Is Word Error Rate Enough? Rethinking Privacy Evaluation in Speech with Entity-Aware Metrics","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.17619","title":"When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}