{"total":65,"rows":[{"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":"2504.08528","title":"On The Landscape of Spoken Language Models: A Comprehensive Survey","created":"2025-04-11","cited_by_count":118,"area":null},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2509.14128","title":"Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST","created":"2025-09-17","cited_by_count":60,"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":"2604.24954","title":"Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence","created":"2026-04-27","cited_by_count":30,"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":"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":"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":"2409.00800","title":"Comparing Discrete and Continuous Space LLMs for Speech Recognition","created":"2024-09-01","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":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2407.10303","title":"Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation","created":"2024-07-14","cited_by_count":11,"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":"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":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2406.07096","title":"Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2505.14887","title":"In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2505.22857","title":"NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding","created":"2025-05-28","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":"2410.17485","title":"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning","created":"2024-10-23","cited_by_count":6,"area":null},{"id":"2506.05191","title":"MokA: Multimodal Low-Rank Adaptation for MLLMs","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2403.09428","title":"Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity","created":"2024-03-14","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":"2409.13523","title":"EMMeTT: Efficient Multimodal Machine Translation Training","created":"2024-09-20","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":"2508.07014","title":"TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree","created":"2025-08-09","cited_by_count":4,"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":"2409.09009","title":"Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2411.00664","title":"Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2507.18263","title":"Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models","created":"2025-07-24","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":"2501.15090","title":"Speech Translation Refinement using Large Language Models","created":"2025-01-25","cited_by_count":2,"area":null},{"id":"2503.00296","title":"Synthetic data enables context-aware bioacoustic sound event detection","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2506.13143","title":"CMU's IWSLT 2025 Simultaneous Speech Translation System","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2601.19194","title":"SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper","created":"2026-01-27","cited_by_count":2,"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":"2506.02012","title":"Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing","created":"2025-05-27","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":"2509.04473","title":"SpeechLLM: Unified Speech and Language Model for Enhanced Multi-Task Understanding in Low Resource Settings","created":"2025-08-29","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":"2510.23849","title":"A Neural Model for Contextual Biasing Score Learning and Filtering","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.18904","title":"MetaSICL: Globalizing Auditory LLMs for Underserved Speakers and Languages via Meta Speech In-Context Learning","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2603.07025","title":"Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2603.17558","title":"Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2606.11033","title":"AuRA: Internalizing Audio Understanding into LLMs as LoRA","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2609.15759","title":"Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2504.05125","title":"Interpretable Style Takagi-Sugeno-Kang Fuzzy Clustering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2508.18701","title":"Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System","created":"2025-08-26","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":"2603.10005","title":"SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2605.11769","title":"Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Control","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.08486","title":"TRADE: Transducer-Augmented Decoder for Speech LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2608.19936","title":"Towards Quantifying Benchmark Optimization in ASR Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.21343","title":"TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.22908","title":"Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.24621","title":"Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.02940","title":"Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.11786","title":"Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.15743","title":"Merging the Knowledge of LLMs for Automatic Speech Recognition","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.18680","title":"HearInContext: A Benchmark for Implicit Context in Speech Recognition","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.33865","title":"In-Context Adaptation of Encoder-Decoder Models in Speech Recognition","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.13411","title":"In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}