{"total":101,"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":"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":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"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":"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":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2507.13264","title":"Voxtral","created":"2025-07-17","cited_by_count":43,"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":"2409.07437","title":"Salmon: A Suite for Acoustic Language Model Evaluation","created":"2024-09-11","cited_by_count":24,"area":null},{"id":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2511.10262","title":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2501.04962","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","created":"2025-01-09","cited_by_count":16,"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":"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":"2503.02769","title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training","created":"2025-03-04","cited_by_count":11,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"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":"2412.08237","title":"TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch","created":"2024-12-11","cited_by_count":10,"area":null},{"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":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2502.19548","title":"When Large Language Models Meet Speech: A Survey on Integration Approaches","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2506.17611","title":"OpusLM: A Family of Open Unified Speech Language Models","created":"2025-06-21","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":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2410.00025","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2412.15712","title":"Contrastive Learning for Task-Independent SpeechLLM-Pretraining","created":"2024-12-20","cited_by_count":8,"area":null},{"id":"2412.17048","title":"Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective","created":"2024-12-22","cited_by_count":8,"area":null},{"id":"2505.19206","title":"SpeakStream: Streaming Text-to-Speech with Interleaved Data","created":"2025-05-25","cited_by_count":8,"area":null},{"id":"2506.15556","title":"PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction","created":"2025-06-18","cited_by_count":8,"area":null},{"id":"2512.20308","title":"SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision","created":"2025-12-23","cited_by_count":8,"area":null},{"id":"2506.08400","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2508.09350","title":"Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling","created":"2025-08-12","cited_by_count":7,"area":null},{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2602.09823","title":"Covo-Audio Technical Report","created":"2026-02-10","cited_by_count":7,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2505.17613","title":"MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation","created":"2025-05-23","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":"2505.23494","title":"Spoken Language Modeling with Duration-Penalized Self-Supervised Units","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2506.01808","title":"NAVER LABS Europe Submission to the Instruction-following Track","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":"2511.11124","title":"AV-Dialog: Spoken Dialogue Models with Audio-Visual Input","created":"2025-11-14","cited_by_count":5,"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":"2507.20091","title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models","created":"2025-07-27","cited_by_count":4,"area":null},{"id":"2601.20417","title":"SpeechMapper: Speech-to-text Embedding Projector for LLMs","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2602.16687","title":"Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2411.07607","title":"CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR","created":"2024-11-12","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":"2503.06211","title":"LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models","created":"2025-03-08","cited_by_count":3,"area":null},{"id":"2505.14438","title":"S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2505.18644","title":"Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2506.10299","title":"Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2509.14882","title":"Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling","created":"2025-09-18","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":"2601.11141","title":"FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","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":"2509.00503","title":"Entropy-based Coarse and Compressed Semantic Speech Representation Learning","created":"2025-08-30","cited_by_count":2,"area":null},{"id":"2602.06602","title":"Scaling Speech Tokenizers with Diffusion Autoencoders","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2605.05927","title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","created":"2026-05-07","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":"2501.06051","title":"Benchmarking Rotary Position Embeddings for Automatic Speech Recognition","created":"2025-01-10","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":"2506.06343","title":"TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.16738","title":"LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2507.12825","title":"Autoregressive Speech Enhancement via Acoustic Tokens","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2508.07375","title":"TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2509.05359","title":"An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.26276","title":"Optimizing Speech Language Models for Acoustic Consistency","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.06673","title":"Heptapod: Language Modeling on Visual Signals","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2601.19399","title":"Residual Tokens Enhance Masked Autoencoders for Speech Modeling","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.05299","title":"WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.06444","title":"Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.08179","title":"Privacy-Preserving End-to-End Full-Duplex Speech Dialogue Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.12350","title":"TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.13262","title":"Evaluation of Audio Language Models for Fairness, Safety, and Security","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.22267","title":"TiCo: Time-Controllable Spoken Dialogue Model","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.06356","title":"In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.06765","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.11192","title":"Exploring Token-Space Manipulation in Latent Audio Tokenizers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2609.14743","title":"Quantifying the Generation Modality Gap in Speech-Text Language Models","created":"2026-09-13","cited_by_count":1,"area":null},{"id":"2407.00486","title":"Towards Massive Multilingual Holistic Bias","created":"2024-06-29","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":"2509.22061","title":"Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2512.01865","title":"Cross-Lingual Interleaving for Speech Language Models","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2603.18612","title":"DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2607.01960","title":"NAVER LABS Europe Submission to the Instruction-following 2026 Short Track","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.04064","title":"Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.11642","title":"ZipCodec: Ultra-Low-Frame-Rate Streaming Speech Coding","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.12563","title":"TokenMapper: A Step Toward Interoperable Speech Token Translation","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.33865","title":"In-Context Adaptation of Encoder-Decoder Models in Speech Recognition","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":"100"}