{"total":19,"rows":[{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56,"area":null},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2306.02207","title":"SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts","created":"2023-06-03","cited_by_count":21,"area":null},{"id":"2406.03150","title":"Sample-specific Masks for Visual Reprogramming-based Prompting","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2309.15223","title":"Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition","created":"2023-09-26","cited_by_count":13,"area":null},{"id":"2410.24018","title":"Bayesian-guided Label Mapping for Visual Reprogramming","created":"2024-10-31","cited_by_count":12,"area":null},{"id":"2306.01015","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2305.11244","title":"A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model","created":"2023-05-18","cited_by_count":8,"area":null},{"id":"2310.09505","title":"Advancing Test-Time Adaptation in Wild Acoustic Test Settings","created":"2023-10-14","cited_by_count":7,"area":null},{"id":"2303.00786","title":"Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2305.11320","title":"Parameter-Efficient Learning for Text-to-Speech Accent Adaptation","created":"2023-05-18","cited_by_count":4,"area":null},{"id":"2402.18275","title":"Exploration of Adapter for Noise Robust Automatic Speech Recognition","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2506.01000","title":"Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2310.02971","title":"Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2506.00620","title":"Model Reprogramming Demystified: A Neural Tangent Kernel Perspective","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2305.11360","title":"Differentially Private Adapters for Parameter Efficient Acoustic Modeling","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2406.17257","title":"Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2409.10515","title":"An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2606.09535","title":"Overcoming Decoder Inconsistencies in Whisper for Dravidian and Low-Resource Languages","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}