{"total":17,"rows":[{"id":"2509.24613","title":"HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2604.21276","title":"Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2604.13979","title":"Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2509.24478","title":"A Text-To-Text Alignment Algorithm for Better Evaluation of Modern Speech Recognition Systems","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2603.05354","title":"Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2604.22817","title":"In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2606.23060","title":"From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.22658","title":"StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2603.05121","title":"Measuring the Redundancy of Decoder Layers in SpeechLLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.27543","title":"AppTek Call-Center Dialogues: A Multi-Accent Long-Form Benchmark for English ASR","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.15984","title":"ROMPAR: Morphological Completion and Demographic Unlearning for Romanian-Accented Speech Recognition","created":"2026-06-14","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":"2609.15743","title":"Merging the Knowledge of LLMs for Automatic Speech Recognition","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.30483","title":"AcoustiClaim: A Numeric Claim Benchmark with Instrument Ground Truth","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38878","title":"Audio Token Attention Is Predictable Before the Language Model Runs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.38897","title":"FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.38976","title":"Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}