{"total":40,"rows":[{"id":"2307.03917","title":"On decoder-only architecture for speech-to-text and large language model integration","created":"2023-07-08","cited_by_count":145,"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":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"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":"2406.10507","title":"Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models","created":"2024-06-15","cited_by_count":29,"area":null},{"id":"2309.07414","title":"PromptASR for contextualized ASR with controllable style","created":"2023-09-14","cited_by_count":19,"area":null},{"id":"2402.13276","title":"When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection","created":"2024-02-17","cited_by_count":17,"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":"2403.18365","title":"BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models","created":"2024-03-27","cited_by_count":15,"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":"2401.12789","title":"Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study","created":"2024-01-23","cited_by_count":12,"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":"2601.20900","title":"Text-only adaptation in LLM-based ASR through text denoising","created":"2026-01-28","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":"2506.05671","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","created":"2025-06-06","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":"2407.17874","title":"Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2309.10707","title":"Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2401.08138","title":"LLMs for Test Input Generation for Semantic Caches","created":"2024-01-16","cited_by_count":4,"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":"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":"2409.13262","title":"Large Language Model Should Understand Pinyin for Chinese ASR Error Correction","created":"2024-09-20","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":"2505.19294","title":"Towards Reliable Large Audio Language Model","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2606.19157","title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2309.09524","title":"Improved Factorized Neural Transducer Model For text-only Domain Adaptation","created":"2023-09-18","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":"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":"2403.13681","title":"Ayn: A Tiny yet Competitive Indian Legal Language Model Pretrained from Scratch","created":"2024-03-20","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":"2507.12252","title":"Improving Contextual ASR via Multi-grained Fusion with Large Language Models","created":"2025-07-16","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":"2509.10452","title":"WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2510.09049","title":"MEC$^3$O: Multi-Expert Consensus for Code Time Complexity Prediction","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2601.16225","title":"ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation","created":"2026-01-16","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":"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}],"next_cursor":null}