{"total":14,"rows":[{"id":"2603.29042","title":"An Empirical Recipe for Universal Phone Recognition","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2601.14046","title":"PRiSM: Benchmarking Phone Realization in Speech Models","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2601.21205","title":"Multilingual Dysarthric Speech Assessment Using Universal Phone Recognition and Language-Specific Phonemic Contrast Modeling","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.01634","title":"HuPER: A Human-Inspired Framework for Phonetic Perception","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2603.23938","title":"OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models","created":"2026-03-25","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":"2606.20179","title":"ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion","created":"2026-06-18","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":"2609.14743","title":"Quantifying the Generation Modality Gap in Speech-Text Language Models","created":"2026-09-13","cited_by_count":1,"area":null},{"id":"2601.02906","title":"Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2607.09020","title":"Phone Segmentation and Recognition through Phonological Activation Mapping","created":"2026-07-10","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":"2609.30924","title":"Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring","created":"2026-09-25","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}