{"total":33,"rows":[{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33,"area":null},{"id":"2410.07400","title":"Advocating Character Error Rate for Multilingual ASR Evaluation","created":"2024-10-09","cited_by_count":24,"area":null},{"id":"2110.05376","title":"Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2401.07506","title":"SeMaScore : a new evaluation metric for automatic speech recognition tasks","created":"2024-01-15","cited_by_count":12,"area":null},{"id":"2211.01722","title":"H_eval: A new hybrid evaluation metric for automatic speech recognition tasks","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2209.10591","title":"Assessing ASR Model Quality on Disordered Speech using BERTScore","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2304.11075","title":"Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2506.04772","title":"Identifying Reliable Evaluation Metrics for Scientific Text Revision","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2211.16319","title":"Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition","created":"2022-11-22","cited_by_count":5,"area":null},{"id":"2307.10587","title":"A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos","created":"2023-07-20","cited_by_count":5,"area":null},{"id":"2510.07437","title":"LASER: An LLM-based ASR Scoring and Evaluation Rubric","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2206.06192","title":"Toward Zero Oracle Word Error Rate on the Switchboard Benchmark","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2604.27542","title":"HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics","created":"2026-04-30","cited_by_count":4,"area":null},{"id":"2511.16544","title":"WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2512.23686","title":"PROFASR-BENCH: A Benchmark for Context-Conditioned ASR in High-Stakes Professional Speech","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2604.21928","title":"Evaluation of Automatic Speech Recognition Using Generative Large Language Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2507.18161","title":"Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges","created":"2025-07-24","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":"2605.03696","title":"A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.03671","title":"A Paradigm for Interpreting Metrics and Identifying Critical Errors in Automatic Speech Recognition","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.16364","title":"WASIL: In-the-Wild Arabic Spoken Interactions with LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2508.04402","title":"What Do Humans Hear When Interacting? Experiments on Selective Listening for Evaluating ASR of Spoken Dialogue Systems","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2603.22709","title":"Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics","created":"2026-03-24","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":"2608.01033","title":"CallScreenBench: Benchmarking Small Language Models as Phone Secretaries","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.25574","title":"Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28916","title":"VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.01737","title":"SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05728","title":"MedWER: A Reproducible, Model-Free Evaluation Protocol for Medical Speech Recognition","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.10714","title":"From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.32082","title":"mu-bench: A Multilingual Utterance Transcription Benchmark","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.17619","title":"When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}