{"total":33,"rows":[{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2412.18161","title":"VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities","created":"2024-12-24","cited_by_count":10,"area":null},{"id":"2412.16507","title":"Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding","created":"2024-12-21","cited_by_count":7,"area":null},{"id":"2506.21555","title":"Efficient Multilingual ASR Finetuning via LoRA Language Experts","created":"2025-06-11","cited_by_count":6,"area":null},{"id":"2505.20006","title":"Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.21576","title":"Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2409.10429","title":"SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2501.06478","title":"Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives","created":"2025-01-11","cited_by_count":4,"area":null},{"id":"2509.02830","title":"SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2602.12911","title":"ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2506.21577","title":"Language-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2603.27981","title":"On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2412.00721","title":"A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2507.03343","title":"SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2507.08477","title":"ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2602.01008","title":"Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages","created":"2026-02-01","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":"2606.07608","title":"Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2609.15758","title":"Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2410.18444","title":"Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2510.22492","title":"The Limits of Data Scaling: Sub-token Utilization and Acoustic Saturation in Multilingual ASR","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2512.17983","title":"Parameter-Efficient Fine-Tuning for HAR: Integrating LoRA and QLoRA into Transformer Models","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2606.06985","title":"Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.14391","title":"Learning to Hear Hesitation: Continual Learning for Disfluency-Aware ASR","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.04814","title":"Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.07294","title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.11587","title":"Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.29239","title":"Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.11302","title":"Automatic Lyric Transcription for Greek Songs: Scaling and Task Composition Effects in Whisper Adaptation","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.11772","title":"Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.18194","title":"T-SANDHI: Tone Sandhi-aware Adaptive Network with Decoupled Hybrid Injection for Low-resource Taiwanese Hokkien Speech Recognition","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20828","title":"Beyond WER: Entity and Disfluency Recall in Accented Conversational ASR","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2610.17019","title":"Understanding Personalization Gains in Whisper","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}