{"total":19,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2204.03067","title":"ByT5 model for massively multilingual grapheme-to-phoneme conversion","created":"2022-04-06","cited_by_count":49,"area":null},{"id":"2103.10291","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"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":"2606.22009","title":"Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study","created":"2026-06-20","cited_by_count":3,"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":"2102.10551","title":"Delhi air quality prediction using LSTM deep learning models with a focus on COVID-19 lockdown","created":"2021-02-21","cited_by_count":1,"area":null},{"id":"2209.11963","title":"A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion","created":"2022-09-24","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":"2312.11920","title":"External Knowledge Augmented Polyphone Disambiguation Using Large Language Model","created":"2023-12-19","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":"2105.12708","title":"Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition","created":"2021-05-26","cited_by_count":0,"area":null},{"id":"2206.02147","title":"Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2210.10200","title":"Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation","created":"2022-10-18","cited_by_count":0,"area":null},{"id":"2410.08974","title":"UniGlyph: A Seven-Segment Script for Universal Language Representation","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2505.19384","title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2512.08006","title":"Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTS","created":"2025-12-08","cited_by_count":0,"area":null}],"next_cursor":null}