{"total":16,"rows":[{"id":"2505.23170","title":"ZIPA: A family of efficient models for multilingual phone recognition","created":"2025-05-29","cited_by_count":19,"area":null},{"id":"2510.24992","title":"POWSM: A Phonetic Open Whisper-Style Speech Foundation Model","created":"2025-10-28","cited_by_count":14,"area":null},{"id":"2602.18899","title":"[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic","created":"2026-02-21","cited_by_count":12,"area":null},{"id":"2501.06810","title":"Improving Cross-Lingual Phonetic Representation of Low-Resource Languages Through Language Similarity Analysis","created":"2025-01-12","cited_by_count":5,"area":null},{"id":"2603.29042","title":"An Empirical Recipe for Universal Phone Recognition","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2403.17407","title":"Transcribing Bengali Text with Regional Dialects to IPA using District Guided Tokens","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2604.18204","title":"Hard to Be Heard: Phoneme-Level ASR Analysis of Phonologically Complex, Low-Resource Endangered Languages","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2410.04292","title":"Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset","created":"2024-10-05","cited_by_count":1,"area":null},{"id":"2509.20655","title":"Building Tailored Speech Recognizers for Japanese Speaking Assessment","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2606.16019","title":"Scaling Human and G2P Supervision for Robust Phonetic Transcription","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2606.22824","title":"BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encoder","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2604.27204","title":"Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.16595","title":"ArtNet: A JEPA-Like Articulatory Predictive Framework for Robust Zero-Shot Phoneme Recognition","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2609.29069","title":"BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33060","title":"Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01427","title":"SHAMS: An Audio-Grounded Pronunciation Benchmark for Levantine Arabic","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}