{"total":32,"rows":[{"id":"2204.03067","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","created":"2022-04-06","cited_by_count":49,"area":null},{"id":"2207.13703","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","created":"2022-07-27","cited_by_count":14,"area":null},{"id":"2104.12395","title":"Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis","created":"2021-04-26","cited_by_count":12,"area":null},{"id":"2409.08554","title":"LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2202.11194","title":"r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporation","created":"2022-02-21","cited_by_count":7,"area":null},{"id":"2404.02456","title":"PhonologyBench: Evaluating Phonological Skills of Large Language Models","created":"2024-04-03","cited_by_count":7,"area":null},{"id":"2104.03945","title":"On Biasing Transformer Attention Towards Monotonicity","created":"2021-04-08","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":"2201.10716","title":"Neural Grapheme-to-Phoneme Conversion with Pre-trained Grapheme Models","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2305.10666","title":"A unified front-end framework for English text-to-speech synthesis","created":"2023-05-18","cited_by_count":4,"area":null},{"id":"2502.20047","title":"Connecting the Persian-speaking World through Transliteration","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2510.07520","title":"ParsTranslit: Truly Versatile Tajik-Farsi Transliteration","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2104.04091","title":"Grapheme-to-Phoneme Transformer Model for Transfer Learning Dialects","created":"2021-04-08","cited_by_count":3,"area":null},{"id":"2310.00706","title":"Evaluating Speech Synthesis by Training Recognizers on Synthetic Speech","created":"2023-10-01","cited_by_count":3,"area":null},{"id":"2401.10465","title":"Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2102.08424","title":"Searching for Search Errors in Neural Morphological Inflection","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2206.04922","title":"A Novel Chinese Dialect TTS Frontend with Non-Autoregressive Neural Machine Translation","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2303.01086","title":"LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversion","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2307.16643","title":"Improving grapheme-to-phoneme conversion by learning pronunciations from speech recordings","created":"2023-07-31","cited_by_count":2,"area":null},{"id":"2307.16709","title":"Multilingual context-based pronunciation learning for Text-to-Speech","created":"2023-07-31","cited_by_count":2,"area":null},{"id":"2411.07563","title":"Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2601.01778","title":"BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2208.01371","title":"Multi-Module G2P Converter for Persian Focusing on Relations between Words","created":"2022-08-02","cited_by_count":1,"area":null},{"id":"2308.08442","title":"Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction","created":"2023-08-16","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":"2609.09974","title":"Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2104.08388","title":"Neural String Edit Distance","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2202.00794","title":"Learning to pronounce as measuring cross-lingual joint orthography-phonology complexity","created":"2022-01-29","cited_by_count":0,"area":null},{"id":"2410.05698","title":"A Two-Step Approach for Data-Efficient French Pronunciation Learning","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2505.14814","title":"GraphemeAug: A Systematic Approach to Synthesized Hard Negative Keyword Spotting Examples","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2609.27205","title":"Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}