{"total":94,"rows":[{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2411.00774","title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","created":"2024-11-01","cited_by_count":141,"area":"mllm"},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"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":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100,"area":null},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2501.06282","title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","created":"2025-01-10","cited_by_count":79,"area":"mllm"},{"id":"2505.02625","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","created":"2025-05-05","cited_by_count":76,"area":null},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72,"area":"agents"},{"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":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"id":"2507.13264","title":"Voxtral","created":"2025-07-17","cited_by_count":43,"area":null},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31,"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":"2505.17060","title":"SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation","created":"2025-05-17","cited_by_count":27,"area":null},{"id":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26,"area":"lr"},{"id":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"area":null},{"id":"2411.01834","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","created":"2024-11-04","cited_by_count":23,"area":"alignment"},{"id":"2505.15406","title":"Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models","created":"2025-05-21","cited_by_count":21,"area":"safety"},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2506.13642","title":"Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model","created":"2025-06-16","cited_by_count":18,"area":"mllm"},{"id":"2410.08035","title":"IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities","created":"2024-10-09","cited_by_count":17,"area":null},{"id":"2505.15727","title":"VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2504.04060","title":"VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation","created":"2025-04-05","cited_by_count":16,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2505.17568","title":"JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models","created":"2025-05-23","cited_by_count":16,"area":"safety"},{"id":"2406.12428","title":"PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems","created":"2024-06-18","cited_by_count":14,"area":"mllm"},{"id":"2510.05150","title":"Chronological Thinking in Full-Duplex Spoken Dialogue Language Models","created":"2025-10-02","cited_by_count":14,"area":"lr"},{"id":"2506.20960","title":"OmniEval: A Benchmark for Evaluating Omni-modal Models with Visual, Auditory, and Textual Inputs","created":"2025-06-26","cited_by_count":13,"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":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2503.01879","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2604.12928","title":"MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models","created":"2026-04-14","cited_by_count":12,"area":null},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2506.21463","title":"Aligning Spoken Dialogue Models from User Interactions","created":"2025-06-26","cited_by_count":11,"area":"alignment"},{"id":"2509.02521","title":"FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training","created":"2025-09-02","cited_by_count":11,"area":null},{"id":"2410.13839","title":"Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding","created":"2024-10-17","cited_by_count":10,"area":"inference"},{"id":"2505.02707","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","created":"2025-05-05","cited_by_count":10,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","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":"2507.10859","title":"MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2508.20916","title":"SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement","created":"2025-08-28","cited_by_count":7,"area":null},{"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":"2506.09349","title":"DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations","created":"2025-06-11","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2603.17837","title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2606.14528","title":"BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2410.20336","title":"Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation","created":"2024-10-27","cited_by_count":5,"area":null},{"id":"2505.21724","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.01934","title":"RoboEgo System Card: An Omnimodal Model with Native Full Duplexity","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2510.06195","title":"Latent Speech-Text Transformer","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.16756","title":"End-to-end Listen, Look, Speak and Act","created":"2025-10-19","cited_by_count":5,"area":"moe"},{"id":"2509.09174","title":"EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2510.11098","title":"VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents","created":"2025-10-13","cited_by_count":4,"area":"agents"},{"id":"2602.01030","title":"Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations","created":"2026-02-01","cited_by_count":4,"area":null},{"id":"2606.05121","title":"Audio Interaction Model","created":"2026-06-03","cited_by_count":4,"area":null},{"id":"2609.13814","title":"Realtime-Venus: A full-duplex interaction system with asynchronous delegation","created":"2026-09-12","cited_by_count":4,"area":null},{"id":"2404.10922","title":"Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2412.08274","title":"2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2505.17326","title":"VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering","created":"2025-05-22","cited_by_count":3,"area":"rag"},{"id":"2510.00499","title":"MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2602.07036","title":"MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2506.23670","title":"Efficient Interleaved Speech Modeling through Knowledge Distillation","created":"2025-06-30","cited_by_count":2,"area":"distill"},{"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":"2508.17623","title":"EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Spoken Dialogue Systems","created":"2025-08-25","cited_by_count":2,"area":"lr"},{"id":"2601.10272","title":"MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts","created":"2026-01-15","cited_by_count":2,"area":"mllm"},{"id":"2604.20842","title":"SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2605.27190","title":"Learning When to Think While Listening in Large Audio-Language Models","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2503.22713","title":"Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2504.02064","title":"From Text to Graph: Leveraging Graph Neural Networks for Enhanced Explainability in NLP","created":"2025-04-02","cited_by_count":1,"area":null},{"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":"2509.03526","title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2602.08607","title":"VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling","created":"2026-02-09","cited_by_count":1,"area":"diffusion"},{"id":"2409.10969","title":"Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corpora","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2505.14356","title":"PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2509.09198","title":"GmSLM : Generative Marmoset Spoken Language Modeling","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.23755","title":"Understanding Textual Capability Degradation in Speech LLMs via Parameter Importance Analysis","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2511.08230","title":"VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context","created":"2025-11-11","cited_by_count":0,"area":"mllm"},{"id":"2512.05994","title":"KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.22889","title":"DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2603.09215","title":"SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models","created":"2026-03-10","cited_by_count":0,"area":"inference"},{"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":"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":"2606.22473","title":"Interleaved Speech Language Models Latently Work In Text","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.02763","title":"LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.16870","title":"Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.19932","title":"Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2610.17461","title":"Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions","created":"2026-10-12","cited_by_count":0,"area":"distill"},{"id":"2610.17780","title":"Full-duplex Spoken Language Modeling with Discrete Diffusion","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}