{"total":80,"rows":[{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"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":"2505.13032","title":"MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix","created":"2025-05-19","cited_by_count":117,"area":"lr"},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"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":"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":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2501.07246","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","created":"2025-01-13","cited_by_count":62,"area":"lr"},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59,"area":"lr"},{"id":"2502.13508","title":"VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation","created":"2025-02-19","cited_by_count":51,"area":"vla"},{"id":"2409.12319","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","created":"2024-09-18","cited_by_count":42,"area":"mllm"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2311.02248","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","created":"2023-11-03","cited_by_count":31,"area":"mllm"},{"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":"2310.05863","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","created":"2023-10-09","cited_by_count":21,"area":"mllm"},{"id":"2409.19510","title":"Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning","created":"2024-09-29","cited_by_count":20,"area":"mllm"},{"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":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","cited_by_count":19,"area":null},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"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":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2503.06362","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","created":"2025-03-09","cited_by_count":11,"area":"mllm"},{"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":"2409.15353","title":"Contextualization of ASR with LLM using phonetic retrieval-based augmentation","created":"2024-09-11","cited_by_count":10,"area":null},{"id":"2505.14336","title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach","created":"2025-05-20","cited_by_count":10,"area":"moe"},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2407.03169","title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation","created":"2024-07-03","cited_by_count":9,"area":"lr"},{"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":"2410.06682","title":"Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization","created":"2024-10-09","cited_by_count":8,"area":"mllm"},{"id":"2410.12948","title":"What Do Speech Foundation Models Not Learn About Speech?","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2412.09818","title":"MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models","created":"2024-12-13","cited_by_count":8,"area":"lr"},{"id":"2601.20900","title":"Text-only adaptation in LLM-based ASR through text denoising","created":"2026-01-28","cited_by_count":8,"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":"2505.14286","title":"Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2506.00304","title":"Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2505.21138","title":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2601.06896","title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","created":"2026-01-11","cited_by_count":5,"area":null},{"id":"2407.02005","title":"An End-to-End Speech Summarization Using Large Language Model","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2409.08597","title":"LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation","created":"2024-09-13","cited_by_count":4,"area":"rag"},{"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":"2505.11352","title":"LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2506.08633","title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2508.14130","title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2510.04136","title":"MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition","created":"2025-10-05","cited_by_count":4,"area":"moe"},{"id":"2412.15299","title":"LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration","created":"2024-12-19","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":"2505.19294","title":"Towards Reliable Large Audio Language Model","created":"2025-05-25","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":"2409.16654","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","created":"2024-09-25","cited_by_count":2,"area":"mllm"},{"id":"2412.19304","title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries","created":"2024-12-26","cited_by_count":2,"area":"lr"},{"id":"2501.04038","title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2505.16212","title":"Large Language Models based ASR Error Correction for Child Conversations","created":"2025-05-22","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":"2606.10439","title":"Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling","created":"2026-06-09","cited_by_count":2,"area":"moe"},{"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":"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":"2412.00721","title":"A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2502.09284","title":"SparQLe: Speech Queries to Text Translation Through LLMs","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2510.13281","title":"Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.18393","title":"OCR-Enhanced Multimodal ASR Can Read While Listening","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2601.19451","title":"Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition","created":"2026-01-27","cited_by_count":1,"area":"moe"},{"id":"2607.22100","title":"MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2405.13274","title":"DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2405.18669","title":"Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2508.08027","title":"Bridging ASR and LLMs for Dysarthric Speech Recognition: Benchmarking Self-Supervised and Generative Approaches","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.08095","title":"Dual Information Speech Language Models for Emotional Conversations","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.16188","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","created":"2025-08-22","cited_by_count":0,"area":"mllm"},{"id":"2601.01121","title":"Listen, Attend, Understand: a Regularization Technique for Stable E2E Speech Translation Training on High Variance labels","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.06199","title":"FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2602.21646","title":"Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion","created":"2026-02-25","cited_by_count":0,"area":"mllm"},{"id":"2603.05121","title":"Measuring the Redundancy of Decoder Layers in SpeechLLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.06487","title":"Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2606.10368","title":"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2610.04333","title":"Factorized Delayed Streams Modeling for LLM-based Streaming ASR","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}