{"total":106,"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":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"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":"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":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"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":"2402.04636","title":"TransLLaMa: LLM-based Simultaneous Translation System","created":"2024-02-07","cited_by_count":34,"area":null},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34,"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":"2312.13585","title":"Speech Translation with Large Language Models: An Industrial Practice","created":"2023-12-21","cited_by_count":28,"area":null},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"area":null},{"id":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","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":"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":"2402.07658","title":"The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models","created":"2024-02-12","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":"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":"2505.11079","title":"ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection","created":"2025-05-16","cited_by_count":17,"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":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","cited_by_count":15,"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":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2405.10025","title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","created":"2024-05-16","cited_by_count":14,"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":"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":"2410.03752","title":"Efficient Streaming LLM for Speech Recognition","created":"2024-10-02","cited_by_count":12,"area":null},{"id":"2510.22603","title":"Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs","created":"2025-10-26","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":"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":"2408.17431","title":"Advancing Multi-talker ASR Performance with Large Language Models","created":"2024-08-30","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":"2410.21485","title":"SpeechQE: Estimating the Quality of Direct Speech Translation","created":"2024-10-28","cited_by_count":10,"area":null},{"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":"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":"2309.00723","title":"Contextual Biasing of Named-Entities with Large Language Models","created":"2023-09-01","cited_by_count":7,"area":null},{"id":"2309.09843","title":"Instruction-Following Speech Recognition","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2406.15734","title":"RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model","created":"2024-06-22","cited_by_count":7,"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":"2409.11274","title":"Task Arithmetic for Language Expansion in Speech Translation","created":"2024-09-17","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":"2505.14286","title":"Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs","created":"2025-05-20","cited_by_count":6,"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":"2312.16222","title":"Segment Any Events via Weighted Adaptation of Pivotal Tokens","created":"2023-12-24","cited_by_count":5,"area":null},{"id":"2403.14438","title":"A Multimodal Approach to Device-Directed Speech Detection with Large Language Models","created":"2024-03-21","cited_by_count":5,"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":"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":"2501.10542","title":"Improved IR-based Bug Localization with Intelligent Relevance Feedback","created":"2025-01-17","cited_by_count":5,"area":null},{"id":"2405.14259","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2406.11568","title":"Towards an End-to-End Framework for Invasive Brain Signal Decoding with Large Language Models","created":"2024-06-17","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":"2412.16464","title":"Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition","created":"2024-12-21","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":"2508.14130","title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2511.07253","title":"Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models","created":"2025-11-10","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":"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":"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":"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":"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":"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":"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":"2505.03273","title":"SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.10599","title":"UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech","created":"2025-05-15","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":"2603.17109","title":"SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval","created":"2026-03-17","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":"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":"2408.09701","title":"Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2409.08543","title":"ATFLRec: A Multimodal Recommender System with Audio-Text Fusion and Low-Rank Adaptation via Instruction-Tuned Large Language Model","created":"2024-09-13","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":"2506.12537","title":"What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.19159","title":"Enhanced Hybrid Transducer and Attention Encoder Decoder with Text Data","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2509.12647","title":"PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition","created":"2025-09-16","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":"2603.12046","title":"Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.18105","title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","created":"2026-04-20","cited_by_count":1,"area":null},{"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":"2405.01601","title":"Efficient Sample-Specific Encoder Perturbations","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2512.05994","title":"KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.15397","title":"LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.05121","title":"Measuring the Redundancy of Decoder Layers in SpeechLLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.06505","title":"Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning","created":"2026-03-06","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":"2606.25436","title":"Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":"100"}