{"total":78,"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":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"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":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"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":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2410.17799","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","created":"2024-10-23","cited_by_count":60,"area":null},{"id":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50,"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":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2406.03872","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2405.04880","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","created":"2024-05-08","cited_by_count":31,"area":null},{"id":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31,"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":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2406.10735","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","created":"2024-06-15","cited_by_count":24,"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":"2401.00246","title":"Boosting Large Language Model for Speech Synthesis: An Empirical Study","created":"2023-12-30","cited_by_count":21,"area":null},{"id":"2405.15388","title":"Language-Driven Interactive Traffic Trajectory Generation","created":"2024-05-24","cited_by_count":19,"area":null},{"id":"2409.11538","title":"Chain-of-Thought Prompting for Speech Translation","created":"2024-09-17","cited_by_count":17,"area":"lr"},{"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":"2407.21491","title":"Generative Expressive Conversational Speech Synthesis","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2502.13472","title":"FlexDuo: A Pluggable System for Enabling Full-Duplex Capabilities in Speech Dialogue Systems","created":"2025-02-19","cited_by_count":15,"area":null},{"id":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","cited_by_count":14,"area":null},{"id":"2402.01293","title":"Can MLLMs Perform Text-to-Image In-Context Learning?","created":"2024-02-02","cited_by_count":13,"area":"mllm"},{"id":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2407.15415","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","created":"2024-07-22","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":"2312.03668","title":"Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition","created":"2023-12-06","cited_by_count":10,"area":null},{"id":"2409.07841","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","created":"2024-09-12","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":"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":"2405.19041","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","created":"2024-05-29","cited_by_count":9,"area":"synth"},{"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":"2506.15556","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":"2507.22920","title":"Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey","created":"2025-07-21","cited_by_count":8,"area":"mllm"},{"id":"2311.04589","title":"TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models","created":"2023-11-08","cited_by_count":7,"area":"mllm"},{"id":"2503.04724","title":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2406.08112","title":"Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2409.11274","title":"Task Arithmetic for Language Expansion in Speech Translation","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","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":"2412.09168","title":"YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls","created":"2024-12-12","cited_by_count":5,"area":null},{"id":"2504.07402","title":"LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2505.00028","title":"Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation","created":"2025-04-27","cited_by_count":5,"area":"rag"},{"id":"2606.23190","title":"FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech","created":"2026-06-22","cited_by_count":5,"area":"diffusion"},{"id":"2311.04534","title":"Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2406.12434","title":"Towards Audio Codec-based Speech Separation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2505.13338","title":"Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2506.01482","title":"Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2410.22448","title":"A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation","created":"2024-10-29","cited_by_count":3,"area":null},{"id":"2411.08742","title":"A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2505.19294","title":"Towards Reliable Large Audio Language Model","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2406.07801","title":"PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2406.12317","title":"Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2408.10853","title":"Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2412.16771","title":"SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization","created":"2024-12-21","cited_by_count":2,"area":"lr"},{"id":"2503.10211","title":"Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2406.14701","title":"Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions","created":"2024-06-20","cited_by_count":1,"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":"2411.00064","title":"The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2501.09104","title":"A Non-autoregressive Model for Joint STT and TTS","created":"2025-01-15","cited_by_count":1,"area":null},{"id":"2510.04593","title":"UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models","created":"2025-10-06","cited_by_count":1,"area":"diffusion"},{"id":"2604.19635","title":"StarTSE: Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2406.05839","title":"MaLa-ASR: Multimedia-Assisted LLM-Based ASR","created":"2024-06-09","cited_by_count":0,"area":null},{"id":"2606.06559","title":"IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.19141","title":"Geometric Iterative Retrieval for Neural Audio Codec Resynthesis","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.04288","title":"Scalable Context Orchestration for Serving LLMs Over Voice","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.11159","title":"Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.11363","title":"UniData: Universal Multimodal Instruction Generation Pipeline","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}