{"total":45,"rows":[{"id":"2212.10474","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","created":"2022-12-20","cited_by_count":25,"area":null},{"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":"2305.19709","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2311.08323","title":"The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language","created":"2023-11-14","cited_by_count":14,"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":"2409.08554","title":"LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2310.00796","title":"SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2503.04724","title":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2504.03036","title":"IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2406.05547","title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2412.09102","title":"PolyIPA -- Multilingual Phoneme-to-Grapheme Conversion Model","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2601.14046","title":"PRiSM: Benchmarking Phone Realization in Speech Models","created":"2026-01-20","cited_by_count":4,"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":"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":"2511.04139","title":"CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese","created":"2025-11-06","cited_by_count":3,"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":"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":"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":"2409.09891","title":"Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning","created":"2024-09-15","cited_by_count":1,"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":"2412.03877","title":"AyutthayaAlpha: A Thai-Latin Script Transliteration Transformer","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2503.07214","title":"Cross-Lingual IPA Contrastive Learning for Zero-Shot NER","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2505.17513","title":"What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2509.03300","title":"LatPhon: Lightweight Multilingual G2P for Romance Languages and English","created":"2025-09-03","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":"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":"2302.14523","title":"Automatic Heteronym Resolution Pipeline Using RAD-TTS Aligners","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2506.12311","title":"Phonikud: Overcoming Phonetic Underspecification for Hebrew Text-To-Speech","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2509.01391","title":"MixedG2P-T5: G2P-free Speech Synthesis for Mixed-script texts using Speech Self-Supervised Learning and Language Model","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.20086","title":"OLaPh: Optimal Language Phonemizer","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.06932","title":"Symphonym: Universal Phonetic Embeddings for Cross-Script Toponym Matching","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2605.30457","title":"Extracting accent features in spoken Brazilian Portuguese without sociolinguistic labels","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.07300","title":"Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.11681","title":"UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.12911","title":"PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.01238","title":"SPARCLE: SPeaker-aware Aligned Representations via Contrastive Language Embeddings","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2607.02633","title":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.28359","title":"Correlation between prosody and pragmatics: A case study of the discourse marker h\\=al\\=a `now' in Persian","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.12814","title":"FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.19805","title":"Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data","created":"2026-09-17","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},{"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}