{"total":57,"rows":[{"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":"2409.09554","title":"ASR Error Correction using Large Language Models","created":"2024-09-14","cited_by_count":24,"area":null},{"id":"2402.06894","title":"GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators","created":"2024-02-10","cited_by_count":22,"area":null},{"id":"2404.09754","title":"Resilience of Large Language Models for Noisy Instructions","created":"2024-04-15","cited_by_count":20,"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":"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":"2309.04842","title":"Leveraging Large Language Models for Exploiting ASR Uncertainty","created":"2023-09-09","cited_by_count":15,"area":null},{"id":"2310.11532","title":"Multi-stage Large Language Model Correction for Speech Recognition","created":"2023-10-17","cited_by_count":13,"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":"2410.13198","title":"Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation","created":"2024-10-17","cited_by_count":10,"area":"rag"},{"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":"2601.20900","title":"Text-only adaptation in LLM-based ASR through text denoising","created":"2026-01-28","cited_by_count":8,"area":null},{"id":"2412.03075","title":"ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction","created":"2024-12-04","cited_by_count":7,"area":null},{"id":"2505.24347","title":"Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2409.00217","title":"ProGRes: Prompted Generative Rescoring on ASR n-Best","created":"2024-08-30","cited_by_count":6,"area":null},{"id":"2506.11089","title":"Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM","created":"2025-06-05","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":"2501.10734","title":"GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems","created":"2025-01-18","cited_by_count":5,"area":"rag"},{"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":"2407.21414","title":"Towards interfacing large language models with ASR systems using confidence measures and prompting","created":"2024-07-31","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":"2501.17489","title":"Neural Spelling: A Spell-Based BCI System for Language Neural Decoding","created":"2025-01-29","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":"2505.17410","title":"LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context","created":"2025-05-23","cited_by_count":4,"area":"synth"},{"id":"2506.07510","title":"DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2407.13300","title":"Robust ASR Error Correction with Conservative Data Filtering","created":"2024-07-18","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":"2412.15655","title":"MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula","created":"2024-12-20","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":"2309.10524","title":"Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2407.12817","title":"Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition","created":"2024-06-29","cited_by_count":2,"area":null},{"id":"2408.09688","title":"Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2409.17750","title":"Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2411.07563","title":"Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2502.15264","title":"Retrieval-Augmented Speech Recognition Approach for Domain Challenges","created":"2025-02-21","cited_by_count":2,"area":"rag"},{"id":"2503.00162","title":"PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos","created":"2025-02-28","cited_by_count":2,"area":"agents"},{"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":"2510.19471","title":"Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition","created":"2025-10-22","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":"2309.09838","title":"HypR: A comprehensive study for ASR hypothesis revising with a reference corpus","created":"2023-09-18","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":"2408.04174","title":"wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech","created":"2024-08-08","cited_by_count":1,"area":null},{"id":"2410.02239","title":"A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2411.13159","title":"Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2501.05234","title":"Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2506.09175","title":"PHRASED: Phrase Dictionary Biasing for Speech Translation","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2506.11091","title":"Customizing Speech Recognition Model with Large Language Model Feedback","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2512.17247","title":"Incorporating Error Level Noise Embedding for Improving LLM-Assisted Robustness in Persian Speech Recognition","created":"2025-12-19","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":"2605.19711","title":"Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.04680","title":"Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.24915","title":"Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction","created":"2026-06-19","cited_by_count":0,"area":"rag"},{"id":"2608.22872","title":"Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.15056","title":"Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}