{"total":71,"rows":[{"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":"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":"2501.07246","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","created":"2025-01-13","cited_by_count":62,"area":"lr"},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"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":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2505.17568","title":"JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models","created":"2025-05-23","cited_by_count":16,"area":"safety"},{"id":"2510.07497","title":"Can Speech LLMs Think while Listening?","created":"2025-10-08","cited_by_count":16,"area":"lr"},{"id":"2509.14515","title":"From Turn-Taking to Synchronous Dialogue: A Survey of Full-Duplex Spoken Language Models","created":"2025-09-18","cited_by_count":10,"area":null},{"id":"2509.16589","title":"Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data","created":"2025-09-20","cited_by_count":10,"area":"lr"},{"id":"2506.17611","title":"OpusLM: A Family of Open Unified Speech Language Models","created":"2025-06-21","cited_by_count":9,"area":null},{"id":"2508.10027","title":"LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data","created":"2025-08-08","cited_by_count":8,"area":"synth"},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2506.05671","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2506.08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2601.12248","title":"AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering","created":"2026-01-18","cited_by_count":6,"area":null},{"id":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2605.15104","title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","created":"2026-05-14","cited_by_count":5,"area":"agents"},{"id":"2507.19308","title":"The Eloquence team submission for task 1 of MLC-SLM challenge","created":"2025-07-25","cited_by_count":4,"area":null},{"id":"2508.17863","title":"Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2601.14046","title":"PRiSM: Benchmarking Phone Realization in Speech Models","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2508.15418","title":"LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2510.23558","title":"ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2602.00269","title":"VoxServe: Streaming-Centric Serving System for Speech Language Models","created":"2026-01-30","cited_by_count":3,"area":"inference"},{"id":"2506.14190","title":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2506.17351","title":"Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.20850","title":"Can large audio language models understand child stuttering speech? speech summarization, and source separation","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2510.22588","title":"UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2601.11039","title":"SonicBench: Dissecting the Physical Perception Bottleneck in Large Audio Language Models","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2603.16941","title":"The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2606.11219","title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2506.04518","title":"Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model","created":"2025-06-04","cited_by_count":1,"area":null},{"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":"2509.21125","title":"Acoustic-based Gender Differentiation in Speech-aware Language Models","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2511.03361","title":"Open Source State-Of-the-Art Solution for Romanian Speech Recognition","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2603.07599","title":"StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2603.19127","title":"On Optimizing Multimodal Jailbreaks for Spoken Language Models","created":"2026-03-19","cited_by_count":1,"area":"safety"},{"id":"2604.08003","title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2605.30899","title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.11260","title":"RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2607.12290","title":"The Sound of Absence: Audio-Language Embedding Models Struggle with Negation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2607.22100","title":"MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2608.30204","title":"When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.18377","title":"Interactive In-Meeting Speaker Correction with Human Feedback","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2509.22744","title":"Index-MSR: A high-efficiency multimodal fusion framework for speech recognition","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.19326","title":"Slot Filling as a Reasoning Task for SpeechLLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2510.24765","title":"Topic-aware Large Language Models for Summarizing the Lived Healthcare Experiences Described in Health Stories","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.09232","title":"POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2601.09716","title":"Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2602.05106","title":"Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models","created":"2026-02-04","cited_by_count":0,"area":"synth"},{"id":"2602.06180","title":"STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.10468","title":"G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.20433","title":"When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.08384","title":"TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.18159","title":"FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.24806","title":"Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language Models","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.06907","title":"SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.07309","title":"Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.16137","title":"XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2607.10092","title":"Efficiently Adapting Spoken Language Models for the Singaporean Context","created":"2026-07-11","cited_by_count":0,"area":"lr"},{"id":"2607.21180","title":"Safeguards for Speech2Speech LLM-Assistants: A Case Study in Automotive Applications","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2607.21496","title":"Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models","created":"2026-07-23","cited_by_count":0,"area":"mllm"},{"id":"2608.08569","title":"VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference","created":"2026-08-09","cited_by_count":0,"area":"inference"},{"id":"2608.24041","title":"Relative Time Intervals Representation for Word-level Timestamping with Masked Training","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.27817","title":"Auditing generative audio calls for known-task audio-llm evaluation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.11724","title":"The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.28713","title":"Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.34217","title":"Explainable and Generalisable LLM-based Cognitive Decline Detection with Spontaneous Speech","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}