{"total":109,"rows":[{"id":"2408.16725","title":"Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming","created":"2024-08-29","cited_by_count":210,"area":"lr"},{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"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":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2502.11946","title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","created":"2025-02-17","cited_by_count":83,"area":null},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2502.17239","title":"Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction","created":"2025-02-24","cited_by_count":68,"area":null},{"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":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2410.16130","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","created":"2024-10-21","cited_by_count":31,"area":"lr"},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2505.19037","title":"Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models","created":"2025-05-25","cited_by_count":27,"area":null},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"area":null},{"id":"2501.13772","title":"Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models","created":"2025-01-23","cited_by_count":23,"area":"safety"},{"id":"2407.06957","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","created":"2024-07-09","cited_by_count":21,"area":null},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21,"area":"inference"},{"id":"2410.07168","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","created":"2024-10-09","cited_by_count":19,"area":null},{"id":"2510.07978","title":"VoiceAgentBench: Are Voice Assistants ready for agentic tasks?","created":"2025-10-09","cited_by_count":19,"area":"agents"},{"id":"2410.01162","title":"Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2409.08596","title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions","created":"2024-09-13","cited_by_count":17,"area":null},{"id":"2510.13632","title":"Closing the Gap Between Text and Speech Understanding in LLMs","created":"2025-10-15","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":"2607.05369","title":"GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks","created":"2026-07-06","cited_by_count":14,"area":"agents"},{"id":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2409.10999","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2501.04561","title":"OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis","created":"2025-01-08","cited_by_count":10,"area":"alignment"},{"id":"2505.13115","title":"Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"id":"2505.22251","title":"Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2507.05177","title":"OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2507.06256","title":"Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2505.19163","title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","created":"2025-05-25","cited_by_count":8,"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":"2506.04723","title":"Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning","created":"2025-06-05","cited_by_count":7,"area":"lr"},{"id":"2506.16528","title":"Aligning ASR Evaluation with Human and LLM Judgments: Intelligibility Metrics Using Phonetic, Semantic, and NLI Approaches","created":"2025-06-19","cited_by_count":7,"area":null},{"id":"2601.13836","title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs","created":"2026-01-20","cited_by_count":7,"area":"mllm"},{"id":"2408.13891","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","created":"2024-08-25","cited_by_count":6,"area":null},{"id":"2410.15316","title":"Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2512.24052","title":"AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives","created":"2025-12-30","cited_by_count":6,"area":"lr"},{"id":"2603.09232","title":"How Contrastive Decoding Enhances Large Audio Language Models","created":"2026-03-10","cited_by_count":6,"area":null},{"id":"2410.19134","title":"AlignCap: Aligning Speech Emotion Captioning to Human Preferences","created":"2024-10-24","cited_by_count":5,"area":"alignment"},{"id":"2506.01808","title":"NAVER LABS Europe Submission to the Instruction-following Track","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2508.01691","title":"Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe","created":"2025-08-03","cited_by_count":5,"area":null},{"id":"2509.04488","title":"Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2602.17598","title":"The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\\rightarrow$LLM Pipelines?","created":"2026-02-19","cited_by_count":5,"area":null},{"id":"2603.13768","title":"Causal Tracing of Audio-Text Fusion in Large Audio Language Models","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2605.19833","title":"Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2407.09209","title":"Pronunciation Assessment with Multi-modal Large Language Models","created":"2024-07-12","cited_by_count":4,"area":"mllm"},{"id":"2409.14526","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","created":"2024-09-22","cited_by_count":4,"area":"lr"},{"id":"2409.17044","title":"How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2505.17446","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2508.14130","title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2510.04908","title":"How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.26096","title":"ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models","created":"2025-10-30","cited_by_count":4,"area":"safety"},{"id":"2601.20417","title":"SpeechMapper: Speech-to-text Embedding Projector for LLMs","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2602.13891","title":"GSRM: Generative Speech Reward Model for Speech RLHF","created":"2026-02-14","cited_by_count":4,"area":"alignment"},{"id":"2504.11082","title":"DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis","created":"2025-04-15","cited_by_count":3,"area":"mllm"},{"id":"2505.18517","title":"LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2505.19669","title":"Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2505.24691","title":"Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios","created":"2025-05-30","cited_by_count":3,"area":"lr"},{"id":"2506.05121","title":"The NTNU System at the S&I Challenge 2025 SLA Open Track","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2508.04795","title":"Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM","created":"2025-08-06","cited_by_count":3,"area":null},{"id":"2510.13558","title":"Steer-MoE: Efficient Audio-Language Alignment with a Mixture-of-Experts Steering Module","created":"2025-10-15","cited_by_count":3,"area":"moe"},{"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":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","cited_by_count":3,"area":"synth"},{"id":"2604.14604","title":"Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection","created":"2026-04-16","cited_by_count":3,"area":"safety"},{"id":"2409.06635","title":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2503.16474","title":"From Voices to Worlds: Developing an AI-Powered Framework for 3D Object Generation in Augmented Reality","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2503.20990","title":"FinAudio: A Benchmark for Audio Large Language Models in Financial Applications","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2505.13577","title":"VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation","created":"2025-05-19","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":"2507.18061","title":"TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios","created":"2025-07-24","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":"2603.19195","title":"How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2410.13268","title":"Roadmap towards Superhuman Speech Understanding using Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.14100","title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection","created":"2024-11-21","cited_by_count":1,"area":"ssm"},{"id":"2505.18217","title":"ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions Challenge","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.12059","title":"CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2509.03526","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","created":"2025-08-25","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":"2602.09534","title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.17558","title":"Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.17443","title":"Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.09366","title":"Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"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":"2607.00247","title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.05759","title":"How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2505.04723","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","created":"2025-05-07","cited_by_count":0,"area":"inference"},{"id":"2506.09556","title":"MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.13396","title":"Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR","created":"2025-06-16","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":"2602.07211","title":"Equipping LLM with Directional Multi-Talker Speech Understanding Capabilities","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.12714","title":"ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2604.00489","title":"Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2606.12199","title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.25444","title":"Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.08117","title":"COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":"100"}