{"total":15,"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":"2601.14046","title":"PRiSM: Benchmarking Phone Realization in Speech Models","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2506.04711","title":"LLM-based phoneme-to-grapheme for phoneme-based speech recognition","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2507.06249","title":"Pronunciation-Lexicon Free Training for Phoneme-based Crosslingual ASR via Joint Stochastic Approximation","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2602.19574","title":"CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment","created":"2026-02-23","cited_by_count":3,"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":"2407.13292","title":"Low-Resourced Speech Recognition for Iu Mien Language via Weakly-Supervised Phoneme-based Multilingual Pre-training","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2604.18105","title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","created":"2026-04-20","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":"2603.29217","title":"Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition","created":"2026-03-31","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":"2608.01281","title":"Latent Softmax for Data-Efficient Phoneme-Based Multilingual ASR Across Tonal and Non-Tonal Languages","created":"2026-08-02","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}],"next_cursor":null}