{"total":29,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2104.02014","title":"SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition","created":"2021-04-05","cited_by_count":78,"area":null},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69,"area":null},{"id":"2407.08103","title":"Automata-based constraints for language model decoding","created":"2024-07-11","cited_by_count":51,"area":null},{"id":"2102.06380","title":"Neural Inverse Text Normalization","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2104.07777","title":"Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2108.09889","title":"A Unified Transformer-based Framework for Duplex Text Normalization","created":"2021-08-23","cited_by_count":6,"area":null},{"id":"2202.00153","title":"Transformer-based Models of Text Normalization for Speech Applications","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2208.00064","title":"Thutmose Tagger: Single-pass neural model for Inverse Text Normalization","created":"2022-07-29","cited_by_count":5,"area":null},{"id":"2210.15063","title":"Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2211.03721","title":"Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition","created":"2022-11-07","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":"2209.02971","title":"Non-Standard Vietnamese Word Detection and Normalization for Text-to-Speech","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2511.03080","title":"PolyNorm: Few-Shot LLM-Based Text Normalization for Text-to-Speech","created":"2025-11-05","cited_by_count":3,"area":null},{"id":"2203.16954","title":"An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer","created":"2022-03-31","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":"2305.16407","title":"Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2208.10248","title":"Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text","created":"2022-07-24","cited_by_count":1,"area":null},{"id":"2401.06321","title":"Multi-Task Learning for Front-End Text Processing in TTS","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2605.19266","title":"FormalASR: End-to-End Spoken Chinese to Formal Text","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.29534","title":"Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2212.01964","title":"Building Metadata Inference Using a Transducer Based Language Model","created":"2022-12-05","cited_by_count":0,"area":null},{"id":"2312.17660","title":"Normalization of Lithuanian Text Using Regular Expressions","created":"2023-12-29","cited_by_count":0,"area":null},{"id":"2402.01300","title":"Two Approaches to Diachronic Normalization of Polish Texts","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2408.12430","title":"Positional Description for Numerical Normalization","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2603.04145","title":"VietNormalizer: An Open-Source, Dependency-Free Python Library for Vietnamese Text Normalization in TTS and NLP Applications","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2606.24714","title":"CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.21084","title":"The Hidden Cost of Digits: Number Normalization and WER in ASR Systems","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30984","title":"THA: Weighted Finite-State Text Normalization and Inverse Text Normalization for Khmer","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}