{"total":140,"rows":[{"id":"2311.07919","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","created":"2023-11-14","cited_by_count":608,"area":null},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140,"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":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114,"area":null},{"id":"2507.16632","title":"Step-Audio 2 Technical Report","created":"2025-07-22","cited_by_count":105,"area":null},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"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":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"area":null},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"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":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46,"area":null},{"id":"2309.08730","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","created":"2023-09-15","cited_by_count":45,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"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":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"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":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2406.18871","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","created":"2024-06-27","cited_by_count":33,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2406.19388","title":"Taming Data and Transformers for Audio Generation","created":"2024-06-27","cited_by_count":28,"area":null},{"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":"2505.17060","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":"2406.15487","title":"Improving Text-To-Audio Models with Synthetic Captions","created":"2024-06-18","cited_by_count":19,"area":null},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19,"area":null},{"id":"2604.10905","title":"Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music","created":"2026-04-13","cited_by_count":19,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"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":"2409.11369","title":"Learning Spatially-Aware Language and Audio Embeddings","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","cited_by_count":15,"area":null},{"id":"2405.02132","title":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","created":"2024-05-03","cited_by_count":13,"area":null},{"id":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"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":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2310.02050","title":"Tuning Large language model for End-to-end Speech Translation","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2406.11025","title":"Large Language Models for Dysfluency Detection in Stuttered Speech","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2309.09843","title":"Instruction-Following Speech Recognition","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2512.10403","title":"BRACE: A Benchmark for Robust Audio Caption Quality Evaluation","created":"2025-12-11","cited_by_count":7,"area":null},{"id":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","cited_by_count":6,"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":"2412.18566","title":"Zero-resource Speech Translation and Recognition with LLMs","created":"2024-12-24","cited_by_count":6,"area":null},{"id":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"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":"2603.09232","title":"How Contrastive Decoding Enhances Large Audio Language Models","created":"2026-03-10","cited_by_count":6,"area":null},{"id":"2310.00160","title":"Self-Specialization: Uncovering Latent Expertise within Large Language Models","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2312.03632","title":"Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2409.06223","title":"Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models","created":"2024-09-10","cited_by_count":5,"area":null},{"id":"2411.11222","title":"The Sound of Water: Inferring Physical Properties from Pouring Liquids","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2506.09375","title":"CoLMbo: Speaker Language Model for Descriptive Profiling","created":"2025-06-11","cited_by_count":5,"area":null},{"id":"2509.18816","title":"Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2510.04584","title":"Robustness assessment of large audio language models in multiple-choice evaluation","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2510.05542","title":"Sci-Phi: A Large Language Model Spatial Audio Descriptor","created":"2025-10-07","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":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2409.09601","title":"A Survey of Foundation Models for Music Understanding","created":"2024-09-15","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":"2506.08524","title":"Teaching Physical Awareness to LLMs through Sounds","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2508.07273","title":"Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models","created":"2025-08-10","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","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":"2401.04935","title":"Learning Audio Concepts from Counterfactual Natural Language","created":"2024-01-10","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":"2411.15685","title":"State-Space Large Audio Language Models","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2505.18517","title":"LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2506.10423","title":"PAL: Probing Audio Encoders via LLMs -- Audio Information Transfer into LLMs","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2506.14973","title":"Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition","created":"2025-06-17","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":"2601.23161","title":"DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2608.02831","title":"Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning","created":"2026-08-03","cited_by_count":3,"area":null},{"id":"2410.11068","title":"Character-aware audio-visual subtitling in context","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2503.09205","title":"Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.19327","title":"DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding","created":"2025-04-27","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":"2509.05256","title":"Recomposer: Event-roll-guided generative audio editing","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2509.07526","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2509.20641","title":"Investigating Modality Contribution in Audio LLMs for Music","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2602.03023","title":"Rethinking Music Captioning with Music Metadata LLMs","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2406.17272","title":"A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR","created":"2024-06-25","cited_by_count":1,"area":null}],"next_cursor":"100"}