{"total":112,"rows":[{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"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":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"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":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"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":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"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":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"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":"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":"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":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"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":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","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":"2309.07081","title":"Can Whisper perform speech-based in-context learning?","created":"2023-09-13","cited_by_count":35,"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":"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":"2402.15151","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","created":"2024-02-23","cited_by_count":30,"area":null},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"area":null},{"id":"2412.05167","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","created":"2024-12-06","cited_by_count":29,"area":null},{"id":"2402.12025","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","created":"2024-02-19","cited_by_count":23,"area":null},{"id":"2309.10917","title":"End-to-End Speech Recognition Contextualization with Large Language Models","created":"2023-09-19","cited_by_count":22,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"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":"2406.19954","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","created":"2024-06-28","cited_by_count":19,"area":null},{"id":"2411.06437","title":"CTC-Assisted LLM-Based Contextual ASR","created":"2024-11-10","cited_by_count":19,"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":"2411.03866","title":"Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward","created":"2024-11-06","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":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2406.09569","title":"Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time","created":"2024-06-13","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":"2406.16107","title":"Decoder-only Architecture for Streaming End-to-end Speech Recognition","created":"2024-06-23","cited_by_count":13,"area":null},{"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":"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":"2410.03752","title":"Efficient Streaming LLM for Speech Recognition","created":"2024-10-02","cited_by_count":12,"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":"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":"2410.21485","title":"SpeechQE: Estimating the Quality of Direct Speech Translation","created":"2024-10-28","cited_by_count":10,"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":"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":"2408.16542","title":"SALSA: Speedy ASR-LLM Synchronous Aggregation","created":"2024-08-29","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":"2503.10620","title":"From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2411.14842","title":"Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models","created":"2024-11-22","cited_by_count":7,"area":null},{"id":"2508.05149","title":"Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2401.11382","title":"Using Large Language Model for End-to-End Chinese ASR and NER","created":"2024-01-21","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":"2409.11274","title":"Task Arithmetic for Language Expansion in Speech Translation","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2405.15216","title":"Revisiting ASR Error Correction with Specialized Models","created":"2024-05-24","cited_by_count":5,"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":"2411.04699","title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2501.02370","title":"Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison","created":"2025-01-04","cited_by_count":5,"area":null},{"id":"2501.09258","title":"Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition","created":"2025-01-16","cited_by_count":5,"area":null},{"id":"2511.21517","title":"Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation","created":"2025-11-26","cited_by_count":5,"area":null},{"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":"2410.03798","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2412.06967","title":"Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2505.11352","title":"LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2309.15826","title":"Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing","created":"2023-09-27","cited_by_count":3,"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":"2408.00624","title":"SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data","created":"2024-08-01","cited_by_count":3,"area":null},{"id":"2409.08680","title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","created":"2024-09-13","cited_by_count":3,"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":"2503.07078","title":"Linguistic Knowledge Transfer Learning for Speech Enhancement","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2504.15509","title":"SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation","created":"2025-04-22","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":"2506.04711","title":"LLM-based phoneme-to-grapheme for phoneme-based speech recognition","created":"2025-06-05","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":"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":"2510.15851","title":"SpeechLLMs for Large-scale Contextualized Zero-shot Slot Filling","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2510.24247","title":"Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2407.04482","title":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation Models","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2501.15090","title":"Speech Translation Refinement using Large Language Models","created":"2025-01-25","cited_by_count":2,"area":null},{"id":"2508.08131","title":"Optimal Transport Regularization for Speech Text Alignment in Spoken Language Models","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2509.15362","title":"Speech Language Models for Under-Represented Languages: Insights from Wolof","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2510.10329","title":"End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2512.06380","title":"Protecting Bystander Privacy via Selective Hearing in Audio LLMs","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2601.10770","title":"Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2601.20898","title":"Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2603.16889","title":"Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment","created":"2026-02-28","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":"2603.27981","title":"On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2405.10741","title":"SBAAM! Eliminating Transcript Dependency in Automatic Subtitling","created":"2024-05-17","cited_by_count":1,"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":"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},{"id":"2408.08027","title":"Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2409.16005","title":"Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs","created":"2024-09-24","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":"2503.00957","title":"Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks","created":"2025-03-02","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":"2510.13194","title":"StressTransfer: Stress-Aware Speech-to-Speech Translation with Emphasis Preservation","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2512.12769","title":"Adaptive Edge-Cloud Inference for Speech-to-Action Systems Using ASR and Large Language Models","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2605.31432","title":"DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.09470","title":"A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales","created":"2026-06-08","cited_by_count":1,"area":null}],"next_cursor":"100"}